Search

Because the complete decompression of images encoded through the HEVC standard is time-consuming, image retrieval encoded through the HEVC standard is one of the most challenging topics in existing database management. Our proposed method is a content-based image retrieval method in the compressed domain, leveraging feature vectors constructed from the I-frame information encoded in HEVC. We introduce a novel concept called auto-correloblock to form these feature vectors. These feature vectors, which represent HEVC coded images in the compressed domain, are based on block sizes and intra-prediction modes. In our method, we utilize the feature vector of the query image to generate a histogram, which is then compared to the feature vectors of images stored in the database. To evaluate our approach, we conduct experiments using the INRIA HOLIDAY database. The results demonstrate the effectiveness of our proposed method, achieving an ANMRR (Average Normalized Modified Retrieval Rank) of 0.23 in coded image retrieval and outperforms its counterparts in this domain. [ABSTRACT FROM AUTHOR]

The digitization of pathology departments in hospitals around the world is now a reality. The current commercial solutions applied to digitize histopathological samples consist of a robotic microscope with an RGB-type camera attached to it. This technology is very limited in terms of information captured, as it only works with three spectral bands of the visible electromagnetic spectrum. Therefore, we present an automated system that combines RGB and hyperspectral technology. Throughout this work, the hardware of the system and its components are described along with the developed software and a working methodology to ensure the correct capture of histopathological samples. The software is integrated by the controller of the microscope, which features an autofocus functionality, whole slide scanning with a stitching algorithm, and hyperspectral scanning functionality. As a reference, the time to capture and process a complete sample with 20 regions of high biological interest using the proposed method is estimated at a maximum of 79 min, reducing the time required by a manual operator by at least three times. Both hardware and software can be easily adapted to other systems that might benefit from the advantages of hyperspectral technology. [ABSTRACT FROM AUTHOR]

Bird strikes are a substantial aviation safety issue that can result in serious harm to aircraft components and even passenger deaths. In response to this increased tendency, the implementation of new and more efficient detection and prevention technologies becomes urgent. The paper presents a novel deep learning model which is developed to detect and alleviate bird strike issues in airport conditions boosting aircraft safety. Based on an extensive database of bird images having different species and flight patterns, the research adopts sophisticated image augmentation techniques which generate multiple scenarios of aircraft operation ensuring that the model is robust under different conditions. The methodology evolved around the building of a spatiotemporal convolutional neural network which employs spatial attention structures together with dynamic temporal processing to precisely recognize flying birds. One of the most important features of this research is the architecture of its dual-focus model which consists of two components, the attention-based temporal analysis network and the convolutional neural network with spatial awareness. The model's architecture can identify specific features nested in a crowded and shifting backdrop, thereby lowering false positives and improving detection accuracy. The mechanisms of attention of this model itself enhance the model's focus by identifying vital features of bird flight patterns that are crucial. The results are that the proposed model achieves better performance in terms of accuracy and real time responses than the existing bird detection systems. The ablation study demonstrates the indispensable roles of each component, confirming their synergistic effect on improving detection performance. The research substantiates the model's applicability as a part of airport bird strike surveillance system, providing an alternative to the prevention strategy. This work benefits from the unique deep learning feature application, which leads to a large-scale and reliable tool for dealing with the bird strike problem. [ABSTRACT FROM AUTHOR]

Lung cancer is relying as one of the significant and leading cause for the deaths which are based on cancer. So, an effective diagnosis is a crucial step to save the patients who are all dying due to lung cancer. Moreover, the diagnosis must be performed based on the severity of lung cancer and the severity can be addressed with the help of an optimal classification approach. So, this research introduced an Attention based Capsule Network (A‐Caps Net) with dispersed dynamic routing to perform in‐depth classification of the disease affected partitions of the image and results in better classification results. The attention layer with dispersed dynamic routing evaluates the digit capsule from feature vector in a constant manner. As the first stage, data acquisitioned from datasets such as Lung Nodule Analysis‐16 (LUNA‐16), The Cancer Imaging Archive (TCIA) dataset and Lung Image Database Consortium and Image Database Resource Initiative (LIDC‐IDRI). After acquisitioning data, pre‐processing is done to enhance the resolution of the image using Generative Adversarial Network. The pre‐processed output is given as output for extraction of features that takes place using GLCM and VGG‐16 which extracts the low level features and high level features respectively. Finally, categorization of lung cancer is performed using Attention based Capsule Network (A‐Caps Net) with dispersed dynamic routing which categorize the lung cancer as benign and malignant. The results obtained through experimental analysis exhibits that proposed approach attained better accuracy of 99.57%, 99.91% and 99.29% for LUNA‐16, LIDC‐IDRI and TCIA dataset respectively. The classification accuracy achieved by the proposed approach for LUNA‐16 dataset is 99.57% which is comparably higher than DBN, 3D CNN, Squeeze Nodule Net and 3D‐DCNN with multi‐layered filter with accuracies of 99.16%, 97.17% and 94.1% respectively. [ABSTRACT FROM AUTHOR]

In practice, and especially when training deep neural networks, visual recognition rules are often learned based on various sources of information. On the other hand, the recent deployment of facial recognition systems with uneven performances on different population segments has highlighted the representativeness issues induced by a naive aggregation of the datasets. In this paper, we show how biasing models can remedy these problems. Based on the (approximate) knowledge of the biasing mechanisms at work, our approach consists in reweighting the observations, so as to form a nearly debiased estimator of the target distribution. One key condition is that the supports of the biased distributions must partly overlap, and cover the support of the target distribution. In order to meet this requirement in practice, we propose to use a low dimensional image representation, shared across the image databases. Finally, we provide numerical experiments highlighting the relevance of our approach. [ABSTRACT FROM AUTHOR]

This research presents an innovative approach designed to enhance the performance of crater-based navigation systems. The core of this approach revolves around proposing a novel method for calculating and incorporating the degree of perturbation observed in matched craters. The foundation of our algorithm lies in the concept of comparing the similarity of projective invariants between image and database craters during the crater matching process. The degree of perturbation in each extracted crater is quantified and normalized using a multivariate Gaussian model. These values are subsequently employed as observation weights within the navigation system. Simulation results confirm the effectiveness of our approach in accurately computing weights that reflect the varying levels of error between craters. Moreover, when integrated into the navigation system, proposed method substantially elevates navigation performance. [ABSTRACT FROM AUTHOR]

Image retrieval involves searching for images relevant to a user-provided query image. In this paper, we aim to develop a graph-based model with deep representations for Content-Based Image Retrieval (CBIR). Inspired by recent advancements in deep learning, we initially employ a fine-tuned Convolutional Neural Network (CNN) to capture deep semantic features for a specific target image database. Utilizing these learned features, we then introduce an graph-based ranking method for online retrieval. This model's constructed graph is designed to characterize the geometrical structure of the data manifold, facilitating an efficient ranking process. Finally, based on user-provided feedback regarding relevant and irrelevant images, we update the retrieval system in both the deep learning framework and the graph-based ranking model in an offline manner. Extensive simulations confirm the efficiency and effectiveness of our proposed model. [ABSTRACT FROM AUTHOR]

The accurate segmentation and classification of lung nodules using Computed Tomography (CT) scans play a significance part for early diagnosis of lung cancers. But, there are risks of misclassification that occurs due to incorrect suspiciousness of malignancy, alongside the reliance on the nodule size. In this research, the Categorical Hinge Loss Function based Convolutional Neural Network (CHLF-CNN) is proposed for multi-classification of lung nodule. This research comprises five main stages: Primarily, data collection is carried out through the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) as well as Lung Nodule Analysis 2016 (LUNA16) of CT-scan image for validating the model's effectiveness. Next, pre-processing is performed by deploying Median Filter based image denoising and Min-max normalization technique. Then, the pre-processed data is segmented by employing the Firefly Algorithm (FA) with the Cuckoo Search Algorithm (CSA) based Markov Random Field (MRF) approach. Then, feature extraction is carried out by utilizing the shape and texture-based features. Finally, classification is performed to classify the lung nodules into multi-classes. The CHLF-CNN attains a commendable accuracy of 96.54% and 99.56% respectively on the LIDC-IDRI and LUNA16 dataset, as opposed to the existing methods, Deep CNN and Morphology-based CNN (2PMorphCNN). [ABSTRACT FROM AUTHOR]

Today, with the increasing demand for visual perception and high-level computational vision tasks, the field of low-light enhancement is rapidly developing. However, models trained on existing datasets often fail or suffer significant performance degradation in real-world low-light scenarios. This performance degradation is frequently due to the limitations of current databases, which typically contain small quantities of paired images of a single type. This article proposes an unsupervised model with a unique data augmentation technique that transforms a regular image database into a paired image database. By adjusting image parameters during training to change exposure, a regular image database can be converted into a paired one. The model restores low-exposure images by extracting lighting features through comparative learning. Evaluations of the LOL and DIV2K datasets demonstrate the proposed model's effectiveness, achieving notable results in low-light image enhancement. This method removes dataset restrictions, broadening the model's range of applications. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) are used to solve pattern classification problems. As this algorithm is based on establishing a relationship between an image-shaped input and its related output through the CNN structure, the training stage is a significant process in their working basis. This study develops a new-fangled and explainable algorithm to train CNNs. The input filters in the convolution layers are parameterized to keep the filter structure, implementing traditional and explainable image processing filters within the network topology. A back-propagation scheme updates the parameters in the filters and the fully connected section of the CNN. Several traditional image filters (Sobel, averaging, Gaussian, and directional, among others) are used in CNN with a learning strategy that keeps their kernel structures. The method implies that the training of these networks is applied to a single parameter instead of all coefficients in the filters, reducing the uncertainty about how each filter performs the image analysis in CNN. This approach was compared with traditional CNNs considering the analysis of the computational cost (measured in terms of time and floops required for training) and their accuracy results. Three image databases were used to evaluate the proposed algorithm. Using a cross-validation methodology, the new training algorithm based on the filter parameterization achieved higher accuracy (93.7% vs. 91.3% in average). The new algorithm got similar results regarding the computational cost compared to traditional methods. This characteristic makes the proposed training methodology an appropriate option to classify images with more explainable processing at the convolution layers. [ABSTRACT FROM AUTHOR]

Simple Summary: Gastric cancer is a major worldwide health concern, underscoring the importance of early detection to enhance patient outcomes. Traditional histological analysis, while considered the gold standard, is labour intensive and manual. Deep learning (DL) is a potential approach, but existing models fail to extract all of the visual data required for successful categorization. This work overcomes these constraints by using ensemble models that mix different deep-learning architectures to improve classification performance for stomach cancer diagnosis. Using the Gastric Histopathology Sub-Size Images Database, the ensemble models obtained an average accuracy of more than 99% at various resolutions. ResNet50, VGGNet, and ResNet34 performed better than EfficientNet and VitNet, with the ensemble model continuously delivering higher accuracy. These findings show that ensemble models may accurately detect important characteristics from smaller picture patches, allowing pathologists to diagnose stomach cancer early and increasing patient survival rates. Gastric cancer has become a serious worldwide health concern, emphasizing the crucial importance of early diagnosis measures to improve patient outcomes. While traditional histological image analysis is regarded as the clinical gold standard, it is labour intensive and manual. In recognition of this problem, there has been a rise in interest in the use of computer-aided diagnostic tools to help pathologists with their diagnostic efforts. In particular, deep learning (DL) has emerged as a promising solution in this sector. However, current DL models are still restricted in their ability to extract extensive visual characteristics for correct categorization. To address this limitation, this study proposes the use of ensemble models, which incorporate the capabilities of several deep-learning architectures and use aggregate knowledge of many models to improve classification performance, allowing for more accurate and efficient gastric cancer detection. To determine how well these proposed models performed, this study compared them with other works, all of which were based on the Gastric Histopathology Sub-Size Images Database, a publicly available dataset for gastric cancer. This research demonstrates that the ensemble models achieved a high detection accuracy across all sub-databases, with an average accuracy exceeding 99%. Specifically, ResNet50, VGGNet, and ResNet34 performed better than EfficientNet and VitNet. For the 80 × 80-pixel sub-database, ResNet34 exhibited an accuracy of approximately 93%, VGGNet achieved 94%, and the ensemble model excelled with 99%. In the 120 × 120-pixel sub-database, the ensemble model showed 99% accuracy, VGGNet 97%, and ResNet50 approximately 97%. For the 160 × 160-pixel sub-database, the ensemble model again achieved 99% accuracy, VGGNet 98%, ResNet50 98%, and EfficientNet 92%, highlighting the ensemble model's superior performance across all resolutions. Overall, the ensemble model consistently provided an accuracy of 99% across the three sub-pixel categories. These findings show that ensemble models may successfully detect critical characteristics from smaller patches and achieve high performance. The findings will help pathologists diagnose gastric cancer using histopathological images, leading to earlier identification and higher patient survival rates. [ABSTRACT FROM AUTHOR]

Correlated Multimodal Imaging (CMI) gathers information about the same specimen with two or more modalities that-combined-create a composite and complementary view of the sample (including insights into structure, function, dynamics and molecular composition). CMI allows one to reach beyond what is possible with a single modality and describe biomedical processes within their overall spatio-temporal context and gain a mechanistic understanding of cells, tissues, and organisms in health and disease by untangling their molecular mechanisms within their native environment. The field of CMI has grown substantially over the last decade and previously unanswerable biological questions have been solved by applying novel CMI workflows. To disseminate these workflows and comprehensively share the scattered knowledge present within the CMI community, an initiative was started to bring together imaging, image analysis, and biomedical scientists and work towards an open community that promotes and disseminates the field of CMI. This community project was funded for the last 4 years by an EU COST Action called COMULIS (COrrelated MUltimodal imaging in the LIfe Sciences). In this review we share some of the showcases and lessons learnt from the action. We also briefly look ahead at how we anticipate building on this initial initiative. [ABSTRACT FROM AUTHOR]

The main objective of this paper is to present a repository of image databases whose features are augmented with embedded vector field (VF) features. The repository is designed to provide the user with image databases that enhance machine learning (ML) classification. Also, six VFs are provided, and the user can embed them into her/his own image database with the help of software named ELPAC. Three of the VFs generate real-shaped singular points (SPs): springing, sinking, and saddle. The other three VFs generate seven kinds of SPs, which include the real-shaped SPs and four complex-shaped SPs: repelling and attracting (out and in) spirals and clockwise and counterclockwise orbits (centers). Using the repository, this work defines the locations of the SPs according to the image objects and the mappings between the SPs' shapes if separate VFs are embedded into the same image. Next, this paper produces recommendations for the user on how to select the most appropriate VF to be embedded in an image database so that the augmented SP shapes enhance ML classification. Examples of images with embedded VFs are shown in the text to illustrate, support, and validate the theoretical conclusions. Thus, the contributions of this paper are the derivation of the SP locations in an image; mappings between the SPs of different VFs; and the definition of an imprint of an image and an image database in a VF. The advantage of classifying an image database with an embedded VF is that the new database enhances and improves the ML classification statistics, which motivates the design of the repository so that it contains image features augmented with VF features. [ABSTRACT FROM AUTHOR]

The severity of periodontitis can be analyzed by calculating the loss of alveolar crest (ALC) level and the level of bone loss between the tooth's bone and the cemento-enamel junction (CEJ). However, dentists need to manually mark symptoms on periapical radiographs (PAs) to assess bone loss, a process that is both time-consuming and prone to errors. This study proposes the following new method that contributes to the evaluation of disease and reduces errors. Firstly, innovative periodontitis image enhancement methods are employed to improve PA image quality. Subsequently, single teeth can be accurately extracted from PA images by object detection with a maximum accuracy of 97.01%. An instance segmentation developed in this study accurately extracts regions of interest, enabling the generation of masks for tooth bone and tooth crown with accuracies of 93.48% and 96.95%. Finally, a novel detection algorithm is proposed to automatically mark the CEJ and ALC of symptomatic teeth, facilitating faster accurate assessment of bone loss severity by dentists. The PA image database used in this study, with the IRB number 02002030B0 provided by Chang Gung Medical Center, Taiwan, significantly reduces the time required for dental diagnosis and enhances healthcare quality through the techniques developed in this research. [ABSTRACT FROM AUTHOR]

Human beings display the extraordinary ability of grasping and communicating abstract concepts. Yet, no standardized instruments exist to assess this ability. Developing these tools is paramount for understanding abstract representations such as social concepts, with ramifications in educational and clinical settings. Here, we developed an image database depicting abstract social concepts varying in social desirability. We first validated the image database in a sample of neurotypical participants. Then, we applied the database to test different hypotheses regarding how social concepts are represented across samples of adults and children with autism spectrum condition (ASC). Relative to the neurotypicals, we did not observe differences related to ASC in identification performance of the social desirability of the concepts, nor differences in metacognitive ability. However, we observed a preference bias away from prosocial concepts that was linked to individual autistic traits in the neurotypicals, and higher in ASC relative to the neurotypicals both in adults and children. These results indicate that abstract representations such as social concepts are dependent on individual neurodevelopmental traits. The image database thus provides a standardized assessment tool for investigating the representation of abstract social concepts in the fields of psycholinguistics, neuropsychology, neuropsychiatry, and cognitive neuroscience, across different cultures and languages. [ABSTRACT FROM AUTHOR]

Face recognition for surveillance remains a complex challenge due to the disparity between low-resolution (LR) face images captured by surveillance cameras and the typically high-resolution (HR) face images in databases. To address this cross-resolution face recognition problem, we propose a two-stage dual-resolution face network to learn more robust resolution-invariant representations. In the first stage, we pre-train the proposed dual-resolution face network using solely HR images. Our network utilizes a two-branch structure and introduces bilateral connections to fuse the high- and low-resolution features extracted by two branches, respectively. In the second stage, we introduce the triplet loss as the fine-tuning loss function and design a training strategy that combines the triplet loss with competence-based curriculum learning. According to the competence function, the pre-trained model can train first from easy sample sets and gradually progress to more challenging ones. Our method achieves a remarkable face verification accuracy of 99.25% on the native cross-quality dataset SCFace and 99.71% on the high-quality dataset LFW. Moreover, our method also enhances the face verification accuracy on the native low-quality dataset. [ABSTRACT FROM AUTHOR]

Flow field data obtained by particle image velocimetry (PIV) could include isolated large damaged areas that are caused by the refractive index, light transmittance, and tracking capability of particles. The traditional deep learning reconstruction methods of PIV fluid data are all based on the velocity field database, and these methods could not achieve satisfactory results for large flow field missing areas. We propose a new reconstruction method of fluid data using PIV particle images. Since PIV particle images are the source of PIV velocity field data, particle images include more complete underlying information than velocity field data. We study the application of PIV experimental particle database in the reconstruction of flow field data using deep generative networks (GAN). To verify the inpainting effect of velocity field using PIV particle images, we design two semantic inpainting methods based on two GAN models with PIV particle image database and PIV fluid velocity database, respectively. Then, the qualitative and quantitative inpainting results of two PIV databases are compared on different metrics. For the reconstruction of velocity field, the mean relative error of using the particle image database could achieve a 52% reduction compared to a velocity database. For the reconstruction of vorticity field, the maximal and mean relative errors can reduce by 50% when using the particle image database. The maximum inpainting errors of two database inputs are both mainly concentrated on the turbulence vortex area, which means the reconstruction of complex non-Gaussian distribution of turbulence vortex is a problem for semantic inpainting of the experimental data. [ABSTRACT FROM AUTHOR]

Coalbed gas pressure and content are fundamental parameters for mine gas recovery and disaster prevention. In response to the lengthy measurement cycles and low accuracy of existing models, this research proposes a new model for determining coalbed gas pressure and content based on image analysis. Utilizing dual-threshold edge detection and dynamic cycle extraction algorithms, a desorption image database was developed, enabling rapid inversion of gas pressure/content through an enhanced image similarity calculation method and cycle comparison algorithm. Field experiments demonstrate the high accuracy of the image analysis model in determining gas pressure/content, controlling the absolute error of gas pressure below 0.08 MPa and maintaining relative errors of 2.27–8.05%; for gas content, the absolute errors range 0.105–0.674 ml/g, with relative errors of 1.32–8.21%. Compared to previous desorption models, the image analysis model improves accuracy by 6.30% and reduces the measurement time to within 1.5 h, thus facilitating rapid and precise determination of coalbed gas pressure/content. Furthermore, by applying image recognition principles, this study delves into the critical points and significant change areas of the desorption rate curve, providing new insights into gas desorption behavior and expanding the application potential of image analysis technology in coalbed methane recovery. [ABSTRACT FROM AUTHOR]

The automatic analysis of patent publications has potential to accelerate research across various domains, including drug discovery and material science. Within patent documents, crucial information often resides in visual depictions of molecule structures. PatCID (Patent-extracted Chemical-structure Images database for Discovery) allows to access such information at scale. It enables users to search which molecules are displayed in which documents. PatCID contains 81M chemical-structure images and 14M unique chemical structures. Here, we compare PatCID with state-of-the-art chemical patent-databases. On a random set, PatCID retrieves 56.0% of molecules, which is higher than automatically-created databases, Google Patents (41.5%) and SureChEMBL (23.5%), as well as manually-created databases, Reaxys (53.5%) and SciFinder (49.5%). Leveraging state-of-the-art methods of document understanding, PatCID high-quality data outperforms currently available automatically-generated patent-databases. PatCID even competes with proprietary manually-created patent-databases. This enables promising applications for automatic literature review and learning-based molecular generation methods. The dataset is freely accessible for download. The automatic analysis of patent documents has potential to accelerate research in chemistry. Here, the authors leverage advances in document understanding to introduce a dataset (PatCID) which allows searching for molecules displayed in documents. [ABSTRACT FROM AUTHOR]

The research aims to improve the performance of image recognition methods based on a description in the form of a set of keypoint descriptors. The main focus is on increasing the speed of establishing the relevance of object and etalon descriptions while maintaining the required level of classification efficiency. The class to be recognized is represented by an infinite set of images obtained from the etalon by applying arbitrary geometric transformations. It is proposed to reduce the descriptions for the etalon database by selecting the most significant descriptor components according to the information content criterion. The informativeness of an etalon descriptor is estimated by the difference of the closest distances to its own and other descriptions. The developed method determines the relevance of the full description of the recognized object with the reduced description of the etalons. Several practical models of the classifier with different options for establishing the correspondence between object descriptors and etalons are considered. The results of the experimental modeling of the proposed methods for a database including images of museum jewelry are presented. The test sample is formed as a set of images from the etalon database and out of the database with the application of geometric transformations of scale and rotation in the field of view. The practical problems of determining the threshold for the number of votes, based on which a classification decision is made, have been researched. Modeling has revealed the practical possibility of tenfold reducing descriptions with full preservation of classification accuracy. Reducing the descriptions by twenty times in the experiment leads to slightly decreased accuracy. The speed of the analysis increases in proportion to the degree of reduction. The use of reduction by the informativeness criterion confirmed the possibility of obtaining the most significant subset of features for classification, which guarantees a decent level of accuracy. [ABSTRACT FROM AUTHOR]

In the digital age, images are widely used to document events, provide evidence, and communicate information. Ensuring the authenticity of digital images is crucial to maintaining trust and integrity in various domains, including journalism, forensics, legal proceedings, and historical documentation. In this research, a PeCA-DCNN model for digital image detection is proposed, employing a hybrid approach. Initially, the data from image forgery databases is collected and preprocessed to eliminate noise and artefacts. Subsequently, the Viola–Jones algorithm detects frontal faces, and feature extraction is performed using pre-trained models VGG-16 and Resnet-101. To reduce the computational overhead, feature extraction is performed and generates a feature vector. The PeCA algorithm, combined with an adaptive self-boosted DCNN, is used to classify fake and genuine images. The PeCA algorithm enhances model performance by adjusting classifier parameters’ weights and biases. When evaluating the PeCA-DCNN, significant improvements in accuracy, sensitivity, and specificity are obtained with enhancement rates of 1.48, 3.06, and 0.05 in an 80% training scenario, and 3.92, 3.24, and 2.22 in k-fold cross-validation. These results demonstrate the effectiveness of the proposed approach compared to existing techniques. [ABSTRACT FROM AUTHOR]

The first step in spatial normalization of magnetic resonance (MR) images commonly is an affine transformation, which may be vulnerable to image imperfections (such as inhomogeneities or “unusual” heads). Additionally, common software solutions use internal starting estimates to allow for a more efficient computation, which may pose a problem in datasets not conforming to these assumptions (such as those from children). In this technical note, three main questions were addressed: one, does the affine spatial normalization step implemented in SPM12 benefit from an initial inhomogeneity correction. Two, does using a complexity-reduced image version improve robustness when matching “unusual” images. And three, can a blind “brute-force” application of a wide range of parameter combinations improve the affine fit for unusual datasets in particular. A large database of 2081 image datasets was used, covering the full age range from birth to old age. All analyses were performed in Matlab. Results demonstrate that an initial removal of image inhomogeneities improved the affine fit particularly when more inhomogeneity was present. Further, using a complexity-reduced input image also improved the affine fit and was beneficial in younger children in particular. Finally, blindly exploring a very wide parameter space resulted in a better fit for the vast majority of subjects, but again particularly so in infants and young children. In summary, the suggested modifications were shown to improve the affine transformation in the large majority of datasets in general, and in children in particular. The changes can easily be implemented into SPM12. [ABSTRACT FROM AUTHOR]

Recently, there has been a rapid increase in the volume of medical image repositories because of the maximized utilization of digitized image data in hospitals. As a result, there is a complexity in querying and handling such large databases, which has led to the development of a novel Content-Based Medical Image Retrieval (CBMIR) technique. In this work, the CBMIR technique is developed using three types of visual features (i.e., color, texture and shape) along with 12 distance measures, and is optimized with the Crossover-Gravitational Search Algorithm (CRO-GSA). For ease, we named this technique Content-Based Medical Image Retrieval using Visual features with CRO-GSA (CBMIRVC). The initial step of our CBMIRVC technique is to extract three types of visual features from the images. Then, each type of feature is employed with a suitable distance measure, which is used for the computation of image similarities between the medical images in the database and a provided query image. The optimization of our proposed CBMIRVC technique is done by the CRO-GSA algorithm. This algorithm optimizes the CBMIRVC technique by identifying the optimal combinations of visual features and similarity measures. Additionally, optimal weights are computed in accordance with the three types of features for the three similarities. Experimental validations were done using retrieved cancer-related and endoscopic color images from databases holding numerous image categories. The experimental outcome shows that our proposed CBMIRVC technique outperforms other conventional image retrieval techniques by effectively retrieving similar images from large databases. [ABSTRACT FROM AUTHOR]

Deep Hashing is widely used for large-scale image-retrieval tasks to speed up the retrieval process. Current deep hashing methods are mainly based on the Convolutional Neural Network (CNN) or Vision Transformer (VIT). They only use the local or global features for low-dimensional mapping and only use the similarity loss function to optimize the correlation between pairwise or triplet images. Therefore, the effectiveness of deep hashing methods is limited. In this paper, we propose a dual-stream correlation-enhanced deep hashing framework (DSCEH), which uses the local and global features of the image for low-dimensional mapping and optimizes the correlation of images from the model architecture. DSCEH consists of two main steps: model training and deep-hash-based retrieval. During the training phase, a dual-network structure comprising CNN and VIT is employed for feature extraction. Subsequently, feature fusion is achieved through a concatenation operation, followed by similarity evaluation based on the class token acquired from VIT to establish edge relationships. The Graph Convolutional Network is then utilized to enhance correlation optimization between images, resulting in the generation of high-quality hash codes. This stage facilitates the development of an optimized hash model for image retrieval. In the retrieval stage, all images within the database and the to-be-retrieved images are initially mapped to hash codes using the aforementioned hash model. The retrieval results are subsequently determined based on the Hamming distance between the hash codes. We conduct experiments on three datasets: CIFAR-10, MSCOCO, and NUSWIDE. Experimental results show the superior performance of DSCEH, which helps with fast and accurate image retrieval. [ABSTRACT FROM AUTHOR]

It is currently unknown whether cancer and cancer treatment affect age-related skeletal changes used in the biological profile for skeletonized remains. This research examines the effects of cancer on skeletal age estimation using computed tomography (CT) scans of the pubic symphyses for 307 individuals from the New Mexico Descendent Image Database. The Suchey–Brooks method was applied to 125 individuals without documented cancer and 182 individuals with documented cancer. Individuals were correctly aged if their chronological age fell within the original study's 95% prediction range. Though not statistically significant, the results show that females with cancer were aged correctly 74.7% of the time, and females without cancer were aged correctly 85.1% of the time; males with cancer were aged correctly 46.0% of the time, and males without cancer were aged correctly 55.7% of the time. Additionally, a total of 30 individuals were reanalyzed to examine intraobserver error, and a Cohen's kappa value of k = 0.600 indicated a moderate level of agreement. While no statistical differences were found between cancer and control groups, CT scans may lack the resolution needed to visualize the nuanced effects of bone mineral density loss, if present, and the overall quality of bone, despite their proven utility in dry-bone skeletal analyses. [ABSTRACT FROM AUTHOR]

Purpose: Radical surgery is the primary treatment for early-stage resectable lung cancer, yet recurrence after curative surgery is not uncommon. Identifying patients at high risk of recurrence using preoperative computed tomography (CT) images could enable more aggressive surgical approaches, shorter surveillance intervals, and intensified adjuvant treatments. This study aims to analyze lung cancer sites in CT images to predict potential recurrences in high-risk individuals. Methods: We retrieved anonymized imaging and clinical data from an institutional database, focusing on patients who underwent curative pulmonary resections for non-small cell lung cancers. Our study used a deep learning model, the Mask Region-based Convolutional Neural Network (MRCNN), to predict cancer locations and assign recurrence classification scores. To find optimized trained weighted values in the model, we developed preprocessing python codes, adjusted dynamic learning rate, and modifying hyper parameter in the model. Results: The model training completed; we performed classifications using the validation dataset. The results, including the confusion matrix, demonstrated performance metrics: bounding box (0.390), classification (0.034), mask (0.266), Region Proposal Network (RPN) bounding box (0.341), and RPN classification (0.054). The model successfully identified lung cancer recurrence sites, which were then accurately mapped onto chest CT images to highlight areas of primary concern. Conclusion: The trained model allows clinicians to focus on lung regions where cancer recurrence is more likely, acting as a significant aid in the detection and diagnosis of lung cancer. Serving as a clinical decision support system, it offers substantial support in managing lung cancer patients. [ABSTRACT FROM AUTHOR]

Leaf senescence is a complex trait which becomes crucial for grain filling because photoassimilates are translocated to the seeds. Therefore, a correct sync between leaf senescence and phenological stages is necessary to obtain increasing yields. In this study, we evaluated the performance of five deep machine-learning methods for the evaluation of the phenological stages of sunflowers using images taken with cell phones in the field. From the analysis, we found that the method based on the pre-trained network resnet50 outperformed the other methods, both in terms of accuracy and velocity. Finally, the model generated, Sunpheno, was used to evaluate the phenological stages of two contrasting lines, B481_6 and R453, during senescence. We observed clear differences in phenological stages, confirming the results obtained in previous studies. A database with 5000 images was generated and was classified by an expert. This is important to end the subjectivity involved in decision making regarding the progression of this trait in the field and could be correlated with performance and senescence parameters that are highly associated with yield increase. [ABSTRACT FROM AUTHOR]

With the continuous advancement of the economy and technology, the number of cars continues to increase, and the traffic congestion problem on some key roads is becoming increasingly serious. This paper proposes a new vehicle information feature map (VIFM) method and a multi-branch convolutional neural network (MBCNN) model and applies it to the problem of traffic congestion detection based on camera image data. The aim of this study is to build a deep learning model with traffic images as input and congestion detection results as output. It aims to provide a new method for automatic detection of traffic congestion. The deep learning-based method in this article can effectively utilize the existing massive camera network in the transportation system without requiring too much investment in hardware. This study first uses an object detection model to identify vehicles in images. Then, a method for extracting a VIFM is proposed. Finally, a traffic congestion detection model based on MBCNN is constructed. This paper verifies the application effect of this method in the Chinese City Traffic Image Database (CCTRIB). Compared to other convolutional neural networks, other deep learning models, and baseline models, the method proposed in this paper yields superior results. The method in this article obtained an F1 score of 98.61% and an accuracy of 98.62%. Experimental results show that this method effectively solves the problem of traffic congestion detection and provides a powerful tool for traffic management. [ABSTRACT FROM AUTHOR]

Data visualization has several advantages, such as representing vast amounts of data and visually demonstrating patterns within it. Manifold learning methods help us estimate lower-dimensional representations of data, thereby enabling more effective visualizations. In data analysis, relying on a single view can often lead to misleading conclusions due to its limited perspective. Hence, leveraging multiple views simultaneously and interactively can mitigate this risk and enhance performance by exploiting diverse information sources. Additionally, incorporating different views concurrently during the graph construction process using interactive visualization approach has improved overall performance. In this paper, we introduce a novel algorithm for joint consistent graph construction and label estimation. Our method simultaneously constructs a unified graph and predicts the labels of unlabeled samples. Furthermore, the proposed approach estimates a projection matrix that enables the prediction of labels for unseen samples. Moreover, it incorporates the information in the label space to further enhance the accuracy. In addition, it merges the information in different views along with the labels to construct a consensus graph. Experimental results conducted on various image databases demonstrate the superiority of our fusion approach compared to using a single view or other fusion algorithms. This highlights the effectiveness of leveraging multiple views and simultaneously constructing a unified graph for improved performance in data classification and visualization tasks in semi-supervised contexts. [ABSTRACT FROM AUTHOR]

The limited availability of specialized image databases (particularly in hospitals, where tools vary between providers) makes it difficult to train deep learning models. This paper presents a few-shot learning methodology that uses a pre-trained ResNet integrated with an encoder as a backbone to encode conditional shape information for the classification of neonatal resuscitation equipment from less than 100 natural images. The model is also strengthened by incorporating a reliability score, which enriches the prediction with an estimation of classification reliability. The model, whose performance is cross-validated, reached a median accuracy performance of over 99% (and a lower limit of 73.4% for the least accurate model/fold) using only 87 meta-training images. During the test phase on complex natural images, performance was slightly degraded due to a sub-optimal segmentation strategy (FastSAM) required to maintain the real-time inference phase (median accuracy 87.25%). This methodology proves to be excellent for applying complex classification models to contexts (such as neonatal resuscitation) that are not available in public databases. Improvements to the automatic segmentation strategy prior to the extraction of conditional information will allow a natural application in simulation and hospital settings. [ABSTRACT FROM AUTHOR]

Content-based image retrieval (CBIR) is a significant research area focused on developing effective techniques for managing large image collections and facilitating efficient retrieval. The primary steps in CBIR involve extracting features from both query and database images and identifying database images with similar extracted features to the query image. The choice of feature extraction methods is crucial, and similarity matching is equally important. The quality of retrieval results depends on the design of the similarity matching process, as it determines how well the system matches the query image's features with those in the database, ranks highly matched database images, and presents them in the retrieval process. In this paper, an innovative content-based image retrieval framework is proposed, which is known as 'SOM based multi-stage CBIR method using the features of CPVTH, POPMV and MDLBP integrated with Multi-Query (CBIR_SCPMMQ).' By incorporating the core concepts of CPVTH, POPMV, MDLBP, and SOM, along with a multi-stage and multi-query-based retrieval system, this proposed CBIR framework offers a dynamic approach to the world of computer vision. Experimental tests on various image databases, including natural, medical, remote sensing, and texture images, have shown that CBIR_SCPMMQ outperforms the existing CBIR methods in terms of precision and retrieval accuracy. The proposed CBIR_SCPMMQ method demonstrates the improvements in precision by 9.03%, recall by 8.3%, sensitivity by 8.6%, accuracy by 2.01%, and FScore by 8.02%. Therefore, the proposed CBIR_SCPMMQ method outperforms other established CBIR techniques. [ABSTRACT FROM AUTHOR]

Although CNN shows high performance in the image recognition field, it has great disadvantages. They are to take a long time to perform machine learning due to a lack of system resources, and to consume a lot of power due to the great volume of computation. A convolution layer is a key element of convolutional neural network processing. This paper presents a convolution layer hardware using processing elements with a low-power multiplier. The low-power multiplier reduces the switching activity by increasing the exchange rate between the multiplier and multiplicand. The proposed convolution layer hardware was implemented on the Intel DE1-SoC FPGA Board using Verilog-HDL. The performance was verified by comparing the exchange rate with the existing multipliers when performing multiplications to process convolutional operations for the MNIST image database. [ABSTRACT FROM AUTHOR]

This research paper presents a modified blind and robust image watermarking scheme that combines dual-tree complex wavelet transform (DTCWT) and discrete cosine transform (DCT) domains. A key challenge for researchers is to determine the optimal locations for embedding watermarks in the low-frequency coefficients of the hybrid domains, ensuring both imperceptibility and security. To identify the most effective sequence for the watermark embedding process, a differential approach is implemented on two correlated DCT-transformed vectors derived from DTCWT wavelet low-frequency coefficients. The watermark data does not need to be extracted from the original image. The proposed scheme aims to assess the efficiency improvement against various image processing attacks. We utilized fifteen grayscale images from the UCI-sipi image database, each with a size of 512 × 512 pixels, to evaluate the proposed scheme. The experimental results demonstrate that our scheme outperforms existing schemes in common image attacks such as geometric attacks, compression, filtering, and noise addition. [ABSTRACT FROM AUTHOR]

In this work, we aim to introduce some modifications to the Anam-Net deep neural network (DNN) model for segmenting optic cup (OC) and optic disc (OD) in retinal fundus images to estimate the cup-to-disc ratio (CDR). The CDR is a reliable measure for the early diagnosis of Glaucoma. In this study, we developed a lightweight DNN model for OC and OD segmentation in retinal fundus images. Our DNN model is based on modifications to Anam-Net, incorporating an anamorphic depth embedding block. To reduce computational complexity, we employ a fixed filter size for all convolution layers in the encoder and decoder stages as the network deepens. This modification significantly reduces the number of trainable parameters, making the model lightweight and suitable for resource-constrained applications. We evaluate the performance of the developed model using two publicly available retinal image databases, namely RIM-ONE and Drishti-GS. The results demonstrate promising OC segmentation performance across most standard evaluation metrics while achieving analogous results for OD segmentation. We used two retinal fundus image databases named RIM-ONE and Drishti-GS that contained 159 images and 101 retinal images, respectively. For OD segmentation using the RIM-ONE we obtain an f1-score (F1), Jaccard coefficient (JC), and overlapping error (OE) of 0.950, 0.9219, and 0.0781, respectively. Similarly, for OC segmentation using the same databases, we achieve scores of 0.8481 (F1), 0.7428 (JC), and 0.2572 (OE). Based on these experimental results and the significantly lower number of trainable parameters, we conclude that the developed model is highly suitable for the early diagnosis of glaucoma by accurately estimating the CDR. [ABSTRACT FROM AUTHOR]

Accurate tools are required to acknowledge misleading images in order to maintain image legitimacy, and these tools must allow for legal operations on images. Additionally, after posting their images to the Internet, image owners lose rights over the images because there are no measures in place to safeguard them from misuse. One of the most well-liked techniques for addressing copyright disputes is the use of steganography technologies. The embedded steganography images can, sadly, be easily altered or deleted. To address this problem, this work presents the spiking neural network (SNN) with blockchain for tampered image detection utilizing forensic steganography images. Forensic steganography images that have been altered can be found with this SNN. Using steganography images from the database, SNN is trained in this model. The blockchain stores the owners' access policies. The Python platform is used to implement the proposed strategy. F-measure, specificity, accuracy, precision, recall false positive rate (FPR), and false negative rate (FNR) are used to gauge how well the proposed approach performs. When compared to state-of-the-art approaches, the proposed approach obtained an impressive rise of 98.65%, in classification accuracy. [ABSTRACT FROM AUTHOR]

Background: Process-based teaching is a new education model. SPARK case database is a free medical imaging case database. This manuscript aimed to explore the application of the process-based teaching based on SPARK case database in the practice teaching of radiology in the musculoskeletal system. Methods: 117 third year medical students were included. They were divided into Group A, B, C and D according to the curriculum arrangement. Group A and B attended the experimental class at the same time, A was the experimental group, B was the control group. Group C and D attended experimental classes at the same time, C was the experimental group, D was the control group. The experimental group used SPARK case database, while the control group used traditional teaching model for learning. The four groups of students were respectively tested after the theoretical class, before the experimental class, after the experimental class, and one week after the experimental class to compare the results. Finally, all students used SPARK case database to study, and were tested one month after the experimental class to compare their differences. Results: The scores after the theoretical class of Group A and B were (100.0 ± 25.4), (101.0 ± 23.8)(t=-0.160, P > 0.05), Group C and D were (94.7 ± 23.7), (92.1 ± 18.6)(t = 0.467, P > 0.05). The scores of Group A and B before and after the experimental class and one week after the experimental class were respectively (84.1 ± 17.4), (72.1 ± 21.3)(t = 2.363, P < 0.05), (107.6 ± 14.3), (102.1 ± 18.0)(t = 1.292, P > 0.05), (89.7 ± 24.3), (66.6 ± 23.2)(t = 3.706, P < 0.05). The scores of Group C and D were (94.0 ± 17.3), (72.8 ± 25.5)(t = 3.755, P < 0.05), (107.3 ± 20.3), (93.1 ± 20.9)(t = 2.652, P < 0.05), (100.3 ± 19.7), (77.2 ± 24.0)(t = 4.039, P < 0.05). The scores of Group A and B for one month after the experimental class were (86.6 ± 28.8), (84.5 ± 24.0)(t = 0.297, P > 0.05), and Group C and D were (95.7 ± 20.3), (91.7 ± 23.0)(t = 0.699, P > 0.05). Conclusions: The process-based teaching based on SPARK case database could improve the radiology practice ability of the musculoskeletal system of students. [ABSTRACT FROM AUTHOR]

The Mimbres Black-on-white ceramic tradition that flourished in the region centered in southwest New Mexico ca. AD 750-1130 offers the scholar an almost unrivaled corpus of iconography and has been the subject of many interpretative studies. Unfortunately, much of this research is compromised by the incorporation of vessels from both private and museum collections that lack provenience and provenance information. The publication of privately-held ceramics can increase their market value, and both categories potentially incorporate deceptive post-excavation modifications. Most Mimbres archaeologists have long been aware of this situation, but recent analytical and statistical studies have confirmed these claims. Additionally, the creation of the Mimbres Pottery Images Digital Database (MimPIDD) has made it easier for the researcher to investigate the provenience and provenance of known vessels. This paper argues for studying only vessels with full provenience and provenance, and it proposes a secure dataset thereof for future research. [ABSTRACT FROM AUTHOR]

Image super-resolution (SR) algorithms are placed on high hope to reconstruct ultra-high-definition (UHD) videos from existing low-resolution videos. Efficient image quality assessment (IQA) methods could not only evaluate the performances of SR algorithms but also provide reliable feedback for algorithm optimization. However, only a few IQA databases and metrics have been specially designed for SR images. In this paper, we propose a database SR4KIQA containing 4K pristine images and super-resolution 4K distorted images with mean opinion score (MOS) labels. Distorted SR images are generated by five classic interpolation methods and seven typical DNN-based super-resolution algorithms. Then, a large-scale database SR4K298 owning 16688 pairs of SR distorted images is designed to support the training process of the ranking-based blind image quality assessment (BIQA) metric we proposed. SROCC of our metric Rank-SR has already reached 0.87 on the SR4KIQA database before the fine-tuning, which outperforms the state-of-art IQA metrics. As one of the very first IQA databases for 4K SR images artifacts, our database SR4KIQA has been publicly available on http://www.dx.doi.org/10.11922/sciencedb.00806 to encourage the further study of the research community. [ABSTRACT FROM AUTHOR]

Ants are capable of learning long visually guided foraging routes with limited neural resources. The visual scene memory needed for this behaviour is mediated by the mushroom bodies; an insect brain region important for learning and memory. In a visual navigation context, the mushroom bodies are theorised to act as familiarity detectors, guiding ants to views that are similar to those previously learned when first travelling along a foraging route. Evidence from behavioural experiments, computational studies and brain lesions all support this idea. Here we further investigate the role of mushroom bodies in visual navigation with a spiking neural network model learning complex natural scenes. By implementing these networks in GeNN-a library for building GPU accelerated spiking neural networks-we were able to test these models offline on an image database representing navigation through a complex outdoor natural environment, and also online embodied on a robot. The mushroom body model successfully learnt a large series of visual scenes (400 scenes corresponding to a 27 m route) and used these memories to choose accurate heading directions during route recapitulation in both complex environments. Through analysing our model's Kenyon cell (KC) activity, we were able to demonstrate that KC activity is directly related to the respective novelty of input images. Through conducting a parameter search we found that there is a non-linear dependence between optimal KC to visual projection neuron (VPN) connection sparsity and the length of time the model is presented with an image stimulus. The parameter search also showed training the model on lower proportions of a route generally produced better accuracy when testing on the entire route. We embodied the mushroom body model and comparator visual navigation algorithms on a Quanser Q-car robot with all processing running on an Nvidia Jetson TX2. On a 6.5 m route, the mushroom body model had a mean distance to training route (error) of 0.144 ±0.088 m over 5 trials, which was performance comparable to standard visual-only navigation algorithms. Thus, we have demonstrated that a biologically plausible model of the ant mushroom body can navigate complex environments both in simulation and the real world. Understanding the neural basis of this behaviour will provide insight into how neural circuits are tuned to rapidly learn behaviourally relevant information from complex environments and provide inspiration for creating bio-mimetic computer/robotic systems that can learn rapidly with low energy requirements. [ABSTRACT FROM AUTHOR]

Objective: Aiming at the shortcomings of artificial surgical path planning for the thermal ablation of liver tumors, such as the time-consuming and labor-consuming process, and relying heavily on doctors' puncture experience, an automatic path-planning system for thermal ablation of liver tumors based on CT images is designed and implemented. Methods: The system mainly includes three modules: image segmentation and three-dimensional reconstruction, automatic surgical path planning, and image information management. Through organ segmentation and three- dimensional reconstruction based on CT images, the personalized abdominal spatial anatomical structure of patients is obtained, which is convenient for surgical path planning. The weighted summation method based on clinical constraints and the concept of Pareto optimality are used to solve the multi-objective optimization problem, screen the optimal needle entry path, and realize the automatic planning of the thermal ablation path. The image information database was established to store the information related to the surgical path. Results: In the discussion with clinicians, more than 78% of the paths generated by the planning system were considered to be effective, and the efficiency of system path planning is higher than doctors' planning efficiency. Conclusion: After improvement, the system can be used for the planning of the thermal ablation path of a liver tumor and has certain clinical application value. [ABSTRACT FROM AUTHOR]

The frequent occurrence of landslides poses a serious threat to people's lives and property. In order to evaluate disaster hazards based on remote sensing images via machine learning means, it is essential to establish an image database with manually labeled boundaries of landslides. However, the existing datasets do not cover diverse types of mountainous landslides. To address this issue, we propose a high-resolution (1 m) diverse mountainous landslide remote sensing dataset (DMLD), including 990 landslide instances across different terrain in southwestern China. To evaluate the performance of the DMLD, seven state-of-the-art deep learning models with different loss functions were implemented on it. The experiment results demonstrate not only that all of these deep learning methods with different characteristics can adapt well to the DMLD, but also that the DMLD has potential adaptability to other geographical regions. [ABSTRACT FROM AUTHOR]

Objective: The purpose of this research was to evaluate and select the best architecture among native convolutional neural network (CNN), MobileNetV2, ResNet50V2, and EfficientNetB0 for predicting the endpoint of the high shear wet granulation process, with accuracy as the main evaluation metric. Methods: The dataset was captured from an industrial camera using static image analysis and was manually labeled as “NOT READY” and “READY” according to the traditional endpoint method based on the mixer’s ampere point in the granulator. The dataset contained a total of 180 images, which were split between training and validation sets. Native CNN and TensorFlow Keras application programming interface (API) were utilized with MobileNetV2, EfficientNetB0, and ResNet50V2 as base feature encoders. Hyperparameters, such as final Fully Connected (FC) layer width, dropout rate, and learning rate, were optimized for binary classification using Keras hyper tuning. Results: The best was the native CNN, it was also the fastest among the three other models, taking only 20-30 ms per step for inference during runtime, though it requires 9000 ms time for training, the longest time among the models. It achieved an accuracy of 98%, and a validation accuracy of 97%. Conclusion: The system was able to determine when a wet granulation process has reached its endpoint based on live images from a camera after being trained on previously labeled data. The native CNN was the best model, offering the fastest runtime performance and the highest accuracy. [ABSTRACT FROM AUTHOR]

The paper demonstrates a novel methodology for Content-Based Image Retrieval (CBIR), which shifts the focus from conventional domain-specific image queries to more complex text-based query processing. Latent diffusion models are employed to interpret complex textual prompts and address the requirements of effectively interpreting the complex textual query. Latent Diffusion models successfully transform complex textual queries into visually engaging representations, establishing a seamless connection between textual descriptions and visual content. Custom triplet network design is at the heart of our retrieval method. When trained well, a triplet network will represent the generated query image and the different images in the database. The cosine similarity metric is used to assess the similarity between the feature representations in order to find and retrieve the relevant images. Our experiments results show that latent diffusion models can successfully bridge the gap between complex textual prompts for image retrieval without relying on labels or metadata that are attached to database images. This advancement sets the stage for future explorations in image retrieval, leveraging the generative AI capabilities to cater to the ever-evolving demands of big data and complex query interpretations. [ABSTRACT FROM AUTHOR]

In terms of its significance, the oil & gas industry is ranked among the top global industries. Like any other industry, it also faces various problems, such as leakage of oil and gas pipelines. The detection of such leakage in the pipelines is essential for an industry or plant to operate properly and maintain environmental safety as well as to minimize its supply-chain losses. The undergoing study systematically reviews the literature comprising of more than a decade (2010-2021) span to summarize the systems, methods and techniques used in oil & gas pipeline leakage detection. Likewise, this paper investigates effective and low-cost leakage detection systems for oil & gas pipelines with their pros and cons. The existing methods are classified into three categories based on their technical characteristics, named as hardware-based (where some hardware is deployed for monitoring the leakage), software-based (where some software is deployed for monitoring the leakage), and intelligent based (where some intelligent predictive algorithm is deployed for the leakage detection) techniques. Each technique was reviewed according to the datasets used, preprocessing techniques (mainly used in the intelligent based techniques that are based on the imagery such as image preprocessing largely like image enhancement, image denoising and filtering), investigated classifiers' efficiencies, results, and limitations. A comparative analysis was conducted to help determine which technology is best for a given operational environment, that is software, hardware, intelligent or hybrid. Further, the paper highlights the gaps in the research and unresolved concerns regarding the development of dependable pipeline leak detection systems and suggests possible research directions to mitigate it. [ABSTRACT FROM AUTHOR]

BACKGROUND: The polyphagous mirid bug Apolygus lucorum (Meyer‐Dür) and the green leafhopper Empoasca spp. Walsh are small pests that are widely distributed and important pests of many economically important crops, especially kiwis. Conventional monitoring methods are expensive, laborious and error‐prone. Currently, deep learning methods are ineffective at recognizing them. This study proposes a new deep‐learning‐based YOLOv5s_HSSE model to automatically detect and count them on sticky card traps. RESULTS: Based on a database of 1502 images, all images were collected from kiwi orchards at multiple locations and times. We trained the YOLOv5s model to detect and count them and then changed the activation function to Hard swish in YOLOv5s, introduced the SIoU Loss function, and added the squeeze‐and‐excitation attention mechanism to form a new YOLOv5s_HSSE model. Mean average precision of this model in the test dataset was 95.9%, the recall rate was 93.9% and the frames per second was 155, which are higher than those of other single‐stage deep‐learning models, such as SSD, YOLOv3 and YOLOv4. CONCLUSION: The proposed YOLOv5s_HSSE model can be used to identify and count A. lucorum and Empoasca spp., and it is a new, efficient and accurate monitoring method. Pest detection will benefit from the broader applications of deep learning. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Multiple-point geostatistics (MPS) is an established tool for the uncertainty quantification of Earth systems modeling, particularly when dealing with the complexity and heterogeneity of geological data. This study presents a novel pixel-based MPS method for modeling spatial data using advanced machine-learning algorithms. Pixel-based multiple-point simulation implies the sequential modeling of individual points on the simulation grid, one at a time, by borrowing spatial information from the training image and honoring the conditioning data points. The developed methodology is based on the mapping of the training image patterns database using the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm for dimensionality reduction, and the clustering of patterns by applying the Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, as an efficient unsupervised classification technique. For the automation, optimization, and input parameter tuning, multiple stages are implemented, including entropy-based determination of the template size and a k-nearest neighbors search for clustering parameter selection, to ensure the proposed method does not require the user's interference. The proposed model is validated using synthetic two- and three-dimensional datasets, both for conditional and unconditional simulations, and runtime information is provided. Finally, the method is applied to a case study gold mine for stochastic orebody modeling. To demonstrate the computational efficiency and accuracy of the proposed method, a two-dimensional training image with 101 by 101 pixels is simulated for 100 conditional realizations in 453 s (~4.5 s per realization) using only 361 hard data points (~3.5% of the simulation grid), and the resulting average simulation has a good visual match and only an 11.8% pixel-wise mismatch with the training image. [ABSTRACT FROM AUTHOR]

Compared with traditional 2D images, omnidirectional images (also referred to as 360∘ images) have more complicated perceptual characteristics due to the particularities of imaging and display. How humans perceive omnidirectional images in an immersive environment and form the immersive quality of experience are important problems. Thus, it is crucial to measure the quality of omnidirectional images under different viewing conditions, which suffer from realistic distortions. In this article, we build a large-scale subjective assessment database for omnidirectional images and carry out a comprehensive psychophysical experiment to study the relationships between different factors (viewing conditions and viewing behaviors) and the perceptual quality of omnidirectional images. In addition, we collect both subjective ratings and head movement data. A thorough analysis of the collected subjective data is also provided, where we make several interesting findings. Moreover, with the proposed database, we propose a novel transformer-based omnidirectional image quality assessment model. To be consistent with the human viewing process, viewing conditions and behaviors are naturally incorporated into the proposed model. Specifically, the proposed model mainly consists of three parts: viewport sequence generation, multi-scale feature extraction, and perceptual quality prediction. Extensive experimental results conducted on the proposed database demonstrate the effectiveness of the proposed method over existing image quality assessment methods. [ABSTRACT FROM AUTHOR]

In this article, we study the challenging cross-modal image retrieval task, Composed Query-Based Image Retrieval (CQBIR), in which the query is not a single text query but a composed query, i.e., a reference image, and a modification text. Compared with the conventional cross-modal image-text retrieval task, the CQBIR is more challenging as it requires properly preserving and modifying the specific image region according to the multi-level semantic information learned from the multi-modal query. Most recent works focus on extracting preserved and modified information and compositing it into a unified representation. However, we observe that the preserved regions learned by the existing methods contain redundant modified information, inevitably degrading the overall retrieval performance. To this end, we propose a novel method termed Cross-Modal Attention Preservation (CMAP). Specifically, we first leverage the cross-level interaction to fully account for multi-granular semantic information, which aims to supplement the high-level semantics for effective image retrieval. Furthermore, different from conventional contrastive learning, our method introduces self-contrastive learning into learning preserved information, to prevent the model from confusing the attention for the preserved part with the modified part. Extensive experiments on three widely used CQBIR datasets, i.e., FashionIQ, Shoes, and Fashion200k, demonstrate that our proposed CMAP method significantly outperforms the current state-of-the-art methods on all the datasets. The anonymous implementation code of our CMAP method is available at https://github.com/CFM-MSG/Code_CMAP. [ABSTRACT FROM AUTHOR]

Lung cancer is a leading cause of global mortality rates. Early detection of pulmonary tumors can significantly enhance the survival rate of patients. Recently, various Computer-Aided Diagnostic (CAD) methods have been developed to enhance the detection of pulmonary nodules with high accuracy. Nevertheless, the existing methodologies cannot obtain a high level of specificity and sensitivity. The present study introduces a novel model for Lung Cancer Segmentation and Classification (LCSC), which incorporates two improved architectures, namely the improved U-Net architecture and the improved AlexNet architecture. The LCSC model comprises two distinct stages. The first stage involves the utilization of an improved U-Net architecture to segment candidate nodules extracted from the lung lobes. Subsequently, an improved AlexNet architecture is employed to classify lung cancer. During the first stage, the proposed model demonstrates a dice accuracy of 0.855, a precision of 0.933, and a recall of 0.789 for the segmentation of candidate nodules. The suggested improved AlexNet architecture attains 97.06% accuracy, a true positive rate of 96.36%, a true negative rate of 97.77%, a positive predictive value of 97.74%, and a negative predictive value of 96.41% for classifying pulmonary cancer as either benign or malignant. The proposed LCSC model is tested and evaluated employing the publically available dataset furnished by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). This proposed technique exhibits remarkable performance compared to the existing methods by using various evaluation parameters. [ABSTRACT FROM AUTHOR]