Search

Leaf disease recognition using image processing and deep learning techniques is currently a vibrant research area. Most studies have focused on recognizing diseases from images of whole leaves. This approach limits the resulting models’ ability to estimate leaf disease severity or identify multiple anomalies occurring on the same leaf. Recent studies have demonstrated that classifying leaf diseases based on individual lesions greatly enhances disease recognition accuracy. In those studies, however, the lesions were laboriously cropped by hand. This study proposes a semi-automatic algorithm that facilitates the fast and efficient preparation of datasets of individual lesions and leaf image pixel maps to overcome this problem. These datasets were then used to train and test lesion classifier and semantic segmentation Convolutional Neural Network (CNN) models, respectively. We report that GoogLeNet’s disease recognition accuracy improved by more than 15% when diseases were recognized from lesion images compared to when disease recognition was done using images of whole leaves. A CNN model which performs semantic segmentation of both the leaf and lesions in one pass is also proposed in this paper. The proposed KijaniNet model achieved state-of-the-art segmentation performance in terms of mean Intersection over Union (mIoU) score of 0.8448 and 0.6257 for the leaf and lesion pixel classes, respectively. In terms of mean boundary F1 score, the KijaniNet model attained 0.8241 and 0.7855 for the two pixel classes, respectively. Lastly, a fully automatic algorithm for leaf disease recognition from individual lesions is proposed. The algorithm employs the semantic segmentation network cascaded to a GoogLeNet classifier for lesion-wise disease recognition. The proposed fully automatic algorithm outperforms competing methods in terms of its superior segmentation and classification performance despite being trained on a small dataset.

Automatic image detection is one of the most im- portant areas in computing due to its potential application in numerous real-world scenarios. One important tool to deal with that is called overlap indices. They were introduced as a procedure to provide the maximum lack of knowledge when comparing two fuzzy objects. They have been successfully applied in the following fields: image processing, fuzzy rule-based systems, decision making and computational brain interfaces. This notion of overlap indices is also necessary for applications in which type-2 fuzzy sets are required. In this paper we introduce the notion of type-(2, k) overlap index (k 0, 1, 2) in the setting of type-2 fuzzy sets. We describe both the reasons that have led to this notion and the relationships that naturally arise among the algebraic underlying structures. Finally, we illustrate how type- (2, k) overlap indices can be employed in the setting of fuzzy rule-based systems when the involved objects are type-2 fuzzy sets. This manuscript has been partially supported by Junta de Andalucía by Projects A-FQM-170-UGR20 (Program FEDER Andalucía 2014-2020) and FQM-365 (Andalusian CICYE), and also by Projects PID2020-119478GBI00 and PID2019-108392GB-I00 (AEI/10.13039/501100011033, Ministerio de Ciencia e Innovación), by CNPq (301618/2019-4), FAPERGS (19/2551- 0001660) and grant VEGA 1/0267/21.

New method for Detection wheat stem rust disease using Image processing methods, Converting RGB image To Hue Saturation Value then setting HSV parameters for background deleting. Texture analyses used for feature extractions. Feature selections where used to accelerate accuracy of detection. Backpropagation neural network used for classifications.

COVID-19 is one of the biggest pandemics that the world is facing today, and every day, we are coming up with new challenges in this area. Still, much research is already going on to overcome this pandemic, and we also get succeeded to some extent. Diverse sources such as MRI, CT scanning, blood samples, X-ray image, and many more are available to detect COVID-19. Thus, it can be easily said that through image processing, the classification of COVID-19 can be done. In this study, the COVID-19 detection is done by classifying with the use of a type of convolutional neural network termed a detail-oriented capsule network. Chest CT scan imaging for the prediction of COVID-19 and non-COVID-19 are classified in the present paper using a Detailed Oriented capsule network (DOCN). Accuracy, specificity, and sensitivity are parameters used for model evaluation. The proposed model has achieved 98% accuracy, 81% sensitivity, and 98.4% specificity.

Recently, extraction of text or characters from images has become a wide field of research in the field of image analysis, neural networks, artificial intelligence and machine vision. The aim of character recognition is to extract and recognize the text from images and can be thus used to analyze contents, documents, or retrieve certain information etc. Image analysis has various processes and algorithms available for text extraction like edge detection, point detection, corner detection etc. for extracting the text from images. Many steps are involved in text recognition including pre-processing, segmentation, feature extraction, and classification. This paper addresses FAST algorithm for corner detection applied on the images for text recognition. The FAST algorithm detects and determines the presence of a corner by testing a small area around the potential center of the corner with the help of intensity value. This approach of text recognition can be efficiently used even with images with noise content or blurs.

Determining congestions on intersection roads can significantly improve the performance of a traffic light system. One of the everyday problems on our roads nowadays is the unbalanced traffic on different roads. The blind view of roads and the dependency on the conventional timer-based traffic light systems can cause unnecessary delays on some arterial roads on expense of offering a needless extra pass time on some other secondary minor roads. In this paper, a foreground extraction model has been built in MATLAB platform to measure the congestions on the different roads constructing an intersection. Results show a satisfactory performance in terms of accuracy in counting cars and in consequence reducing the wait time on some major roads. System was tested under different weather and lighting conditions, and results were adequately promising.

Biometrics deals with the recognition of humans based on their unique physical characteristics. It can be based on face identification, iris, fingerprint and DNA. In this paper, we have considered the iris as a source of biometric verification as it is the unique part of eye which can never be altered, and it remains the same throughout the life of an individual. We have proposed the improved iris recognition system including image registration as a main step as well as the edge detection method for feature extraction. The PCA-based method is also proposed as an independent iris recognition method based on a similarity score. Experiments conducted using our own developed database demonstrate that the first proposed system reduced the computation time to 6.56 sec, and it improved the accuracy to 99.73, while the PCA-based method has less accuracy than this system does.

Purpose Leukaemia is diagnosed conventionally by observing the peripheral blood and bone marrow smear using a microscope and with the help of advanced laboratory tests. Image processing-based methods, which are simple, fast, and cheap, can be used to detect and classify leukemic cells by processing and analysing images of microscopic smear. The proposed study aims to classify Acute Lymphoblastic Leukaemia (ALL) by Deep Learning (DL) based techniques. Procedures The study used Deep Convolutional Neural Networks (DNNs) to classify ALL according to WHO classification scheme without using any image segmentation and feature extraction that involves intense computations. Images from an online image bank of American Society of Haematology (ASH) were used for the classification. Findings A classification accuracy of 94.12% is achieved by the study in isolating the B-cell and T-cell ALL images using a pretrained CNN AlexNet as well as LeukNet, a custom-made deep learning network designed by the proposed work. The study also compared the classification performances using three different training algorithms. Conclusions The paper detailed the use of DNNs to classify ALL, without using any image segmentation and feature extraction techniques. Classification of ALL into subtypes according to the WHO classification scheme using image processing techniques is not available in literature to the best of the knowledge of the authors. The present study considered the classification of ALL only, and detection of other types of leukemic images can be attempted in future research.

The Brain Tumor is one of the most serious scenarios associated with the brain where a cluster of abnormal cells grows in an uncontrolled fashion. The field of image processing has experienced remarkable growth in the area of biomedical applications with the invention of different techniques in deep learning. Brain tumor classification and detection is a subject of prime importance where Convolutional Neural Networks (CNN) find application. But the main drawback of the existing technology is that it is complex with a huge number of parameters contributing to high execution time and high system specifications for implementation. In this paper, a novel architecture for Brain tumor classification and tumor type object detection using the RCNN technique is proposed which has been analyzed using two publicly available datasets from Figshare ( Cheng et al., 2017 ) and Kaggle (2020) . Here we aim to decrease the execution time of a conventional RCNN architecture with the use of a low complex framework and propose a system for brain tumor analysis. We first use a Two Channel CNN, a low complex architecture to classify between Glioma and healthy tumor MRI samples which was successfully done with an accuracy of 98.21 percentage. Later this same architecture is used as the feature extractor of an RCNN to detect the tumor regions of the Glioma MRI sample that has been classified from the previous stage and the tumor region is bounded using bounding boxes. Also, this method has been extended to other two types of tumors Meningioma and Pituitary tumor. The methodology was able to achieve very low execution time as compared with the other existing architectures with an average confidence level of 98.83 percentage.

In the medical field, Medical diagnosis using Computed tomography (CT) has become increasingly popular due to their non-invasive approach and quick overall turnaround time. 3D visualization for CT Colonography involves the assessment and diagnosis of a patient to find the presence of cancerous polyps in the colon, by taking a Computed Tomography scan of the patient, and evaluating the reports. This technique reduces evaluation time by allowing the doctors themselves to analyze the CT scans without the need for a radiologist to generate an initial report. This technique also avoids an invasive procedure on the patient. This paper gives the insightsof developing computer aided system for the detection of Polyps in CT Colonography images using the principles of Image Processing and the Deep Learning, specifically an ensemble of Convolutional Neural Networks using GoogleNet architecture and 3D reconstruction of the same. The accuracy achieved by the proposed system for region classification, region 1 polyp detection and region 2 polyp detection are 98.75%, 93.75% and 94.03% respectively, and their F1 Scores are 0.88, 0.82 and 0.84 respectively.

In recent history, Convolutional Neural Networks have attained breakthroughs in addressing many intractable problems in the domain of image processing. But its performance builds upon its chosen hyper parameters and it is a tedious job to manually fine tune these hyper parameters. Hence, in this research, an Automated Hyper-parameter Optimized Convolution Neural Net is proposed which is further applied to uncover the class of skin cancer. The method has utilized a Grey Wolf Optimization algorithm for optimizing the hyper parameters of CNN, by adopting a proper encoding scheme. The effectiveness of the model is verified by comparing it with the performance of Particle Swarm Optimization and Genetic algorithm based hyper-parameter optimized CNN applied on the International Skin Imaging Collaboration skin lesion multi class data set. Simulation results infer that the proposed model is able to produce a testing accuracy up to 98.33% which is around 4% and 1% more compared to PSO and GA based models respectively. Similarly with the proposed model, the testing loss realized is around 0.17% which is 39.2% and 15% less compared to PSO and GA based models respectively. The experimental results clearly demonstrate that the proposed model performs competitively compared to other reported models.

The assurance of secret data transmitted over the Internet and confining its access to explicit grouped information has become a significant security and protection issue. To hide the presence of such information, a robust and blind color image steganography algorithm, using fractal cover images, Singular Value Decomposition (SVD), Integer Wavelet Transform (IWT), and Discrete Wavelet Transform (DWT) is proposed in this paper. The proposed algorithm conceals the color secret image intelligently inside a fractal cover image thus creating a unique stego-image that is virtually a replica of the original cover image. The novelty of this proposed blind image hiding method lies in the fact that a small file size of a unique fractal image can be used to conceal a large amount of information payload. The fractal cover images can be implemented without debasing its quality to make the shrouded information sufficiently strong against image processing attacks. The algorithm possesses features like robustness, imperceptibility, security, and greater hiding capacity due to the application of fractal compression, DWT-SVD, and IWT-SVD hybrid transform schemes. The secret image is inserted in U and V components of the fractal cover with a scaling factor based on the HVS model and a stego-image with sufficiently large keyspace is created. Furthermore, the proposed work compares the performance analysis and security offered by IWT- SVD and DWT- SVD hybrid combinations for different fractal covers using certain metrics like PSNR (Peak Signal to Noise Ratio), MSE (Mean Square Error), SSIM (Structural Similarity Index), BRISQUE (Blind/ Reference less Image Spatial Quality Evaluator) score and Bits per pixel (BPP). The results prove that image degradation is very less (less than 0.6%) in the proposed algorithm even when the secret image file size is more than double the file size of the fractal cover image which also saves the bandwidth and storage requirements.

In image processing, smoke may degrade visibility and deteriorate the performance of high-level vision applications. Therefore, single image smoke removal is crucial for computer vision. Currently, existing smoke removal algorithms mainly leverage handcrafted priors. Moreover, these methods usually apply haze removal methods to perform smoke removal due to the similarity between smoke and haze. However, these methods cannot sufficiently address the degradation of thick smoke and may suffer from residual smoke and color distortion problems due to the non-global and non-homogeneous distribution of smoke. In this paper, to solve the aforementioned problems, an end-to-end deep neural network called DesmokeNet is proposed. We construct a two-stage recovered pipeline to remove the smoke in different thicknesses. The light and thick smoke is first removed locally by the smoke removal network (SRN). The missing pixels in the thick smoke are then recovered by the pixel compensation network (PCN). Moreover, we proposed the thickness-aware pixel loss and the dark channel loss to suppress the residual smoke. To further increase the discriminative ability of the DesmokeNet, we proposed self-attentive feature consensus loss and multi-level contrastive regularization loss to improve the performance of smoke removal. Finally, to train the proposed method, we construct the first large-scale dataset containing synthetic and real-world data. Extensive experiments show that the proposed method outperforms favorably against other state-of-the-art methods quantitatively and qualitatively.

Nowadays, with the advances and use of technological possibilities and devices, the number of digital images is increasing gradually. Computer-aided classification of image types is widely applied in many applications such as medicine, security, and automation. The feature extraction and selection stages have great importance in terms of improving the classification performance as sub-stages of the pattern recognition process. Researchers apply different feature extraction methods for their works due to the requirements. In this study, a novel pattern recognition framework combining diverse and large-scale handcrafted feature extraction methods (shape-based and texture-based) and the selection stage on images is developed. Genetic algorithms are also used for feature selection. In the experimental studies, Flavia leaf recognition, Caltech101 object classification image datasets, and five supervised classification models (random forest, ECOC-SVM, k-nearest neighbor, AdaBoost, classification tree) with different parameters' values are used. The experimental results show that the proposed method achieves 98.39% and 82.77% accuracy rates on Flavia and Caltech101 datasets with the ECOC-SVM model, respectively. The proposed framework is also competitive with the existing state-of-the-art methods in the related literature., Scientific and Technological Research Council of Turkey (TUBITAK) 2211 National Graduate Scholarship Program, The author Erdal TASCI has been supported by the Scientific and Technological Research Council of Turkey (TUBITAK) 2211 National Graduate Scholarship Program.

A noniterative fractional-order (FO) two-dimensional (2-D) adaptive filtering mechanism is proposed in this article. Quartiles-based adaptive textural segmentation is employed for the calculation of texture-dependent FO. Statistically, the quartiles/quintiles/quantiles are cut points for dividing the range of a probability distribution into continuous intervals with equal probabilities. For the purpose of texture-based isolation of the spatial regions, a 2-D textural map is framed by evaluating spatial entropy by considering a pixel-wise local circular neighborhood. A novel end-to-end framework is proposed for FO texture-dependent image sharpening in an independent manner without influencing the other classes of textural regions. A novel inclusion of texture-wise adaptive gamma correction is also proposed in this article by drafting a mechanism where different kinds of textural regions can be separately processed in an independent manner. A novel quintiles-based multiscale Retinex (MSR) inspired approach for reflectance computation is coined in this article for suppressing environmental artifacts and unbalanced/nonuniform illumination. In this context, various scales required for MSR are themselves computed through quartiles-based intensity levels. The proposed model is highly modular. So, it can also be pipelined in a parallel manner, along with any well-established state-of-the-art contrast enhancement approach. Also, this approach is noniterative and highly robust. It can be proposed as an add-on for several possible (as well as pre-existing) image processing procedures. Rigorous comparative evaluations are performed so that the excellence of the proposed approach can be underlined.

Defect detection of trains is of great significance for operation safety and maintenance efficiency for railway maintenance. Nowadays, China railway system utilizes high-speed line scan cameras to capture images of critical parts of moving trains. The visual inspection on the images still heavily relies on manual interpretation. To reduce the labor requirements, we propose a novel two-stage deep learning based framework for component defect detection of moving trains. The proposed framework is composed of two major successive stages: detecting train components by using our proposed hierarchical object detection scheme (HOD), and detecting component defects based on multiple neural networks and image processing methods. Our proposed HOD can effectively detect and localize train components from large to small in a hierarchical way. Furthermore, a gated feature fusion method that can extract and combine the hierarchical contextual features and spatial contexts is also proposed to improve the performance. To the best of our knowledge, it is the first time in the literature that component defect detection of moving trains is systematically analyzed. Extensive experiments on real images from China railway system have demonstrated that our framework outperforms the state-of-the-art baselines significantly.

The limitation to the most commonly used histogram equalization (HE) technique is the inconsideration of the neighborhood info near each pixel for contrast enhancement. This gives rise to noise in the output image. To overcome this effect, a novel joint histogram equalization (JHE) based technique is suggested. The focus is to utilize the information among each pixel and its neighbors, which improves the contrast of an image. The suggested method is developed in a truly two-dimensional domain. The joint histogram is constructed using the original image and its average image. Further, it does not require a target uniform distribution for generating the output. The two-dimensional cumulative distribution function (CDF) is utilized as a mapping function to get the output pixel intensity. Extensive experiments are performed using 300 test images from BSD database. The experimental analysis indicates that the procedure produces better results than the state-of-the-art HE based contrast enhancement algorithms. More significantly, it produces the best results even for images having a narrow dynamic range. The implementation simplicity of the proposed algorithm may attract researchers to explore the idea for new applications in image processing.

Plant height and width is an essential phenotypic parameter that can be used not only as an indicator of overall plant growth but also used to estimate the advanced parameters such as the design of agricultural machines, estimation of yield, and site-specific applications. Presently, chili plant height and width are mostly measured manually, which is laborious and time-consuming process. The goal of this study was to develop and evaluate a real-time phenotyping system using an image processing approach to measure chili plant height and width under field conditions. The image processing algorithm was developed and compiled in the open-source computer vision library (OpenCV) and Python language using PyCharm as an integrated development environment (IDE). The developed image processing algorithm was evaluated in both static and field conditions in two plots of chili plants. The developed system was able to capture a valid image of the chili plant under field conditions and accurately estimate the height and width of the plant with a RMSE in the ranges of 0.30-0.60 cm. The height and width measured by the proposed image processing algorithm were strongly correlated (R2 = 0.80–0.95) with manually measured values. Furthermore, the image processing approach has much more advanced features to measure the more complex geometric traits of plants.

Indiana University-Purdue University Indianapolis (IUPUI), In traffic scene perception for autonomous vehicles, driving videos are available from in-car sensors such as camera and LiDAR for road detection and collision avoidance. There are some existing challenges in computer vision tasks for video processing, including object detection and tracking, semantic segmentation, etc. First, due to that consecutive video frames have a large data redundancy, traditional spatial-to-temporal approach inherently demands huge computational resource. Second, in many real-time scenarios, targets move continuously in the view as data streamed in. To achieve prompt response with minimum latency, an online model to process the streaming data in shift-mode is necessary. Third, in addition to shape-based recognition in spatial space, motion detection also replies on the inherent temporal continuity in videos. While current works either lack long-term memory for reference or consume a huge amount of computation. The purpose of this work is to achieve strongly temporal-associated sensing results in real-time with minimum memory, which is continually embedded to a pragmatic framework for speed and path planning. It takes a temporal-to-spatial approach to cope with fast moving vehicles in autonomous navigation. It utilizes compact road profiles (RP) and motion profiles (MP) to identify path regions and dynamic objects, which drastically reduces video data to a lower dimension and increases sensing rate. Specifically, we sample one-pixel line at each video frame, the temporal congregation of lines from consecutive frames forms a road profile image; while motion profile consists of the average lines by sampling one-belt pixels at each frame. By applying the dense temporal resolution to compensate the sparse spatial resolution, this method reduces 3D streaming data into 2D image layout. Based on RP and MP under various weather conditions, there have three main tasks being conducted to contribute the knowledge domain in perception and planning for autonomous driving. The first application is semantic segmentation of temporal-to-spatial streaming scenes, including recognition of road and roadside, driving events, objects in static or motion. Since the main vision sensing tasks for autonomous driving are identifying road area to follow and locating traffic to avoid collision, this work tackles this problem by using semantic segmentation upon road and motion profiles. Though one-pixel line may not contain sufficient spatial information of road and objects, the consecutive collection of lines as a temporal-spatial image provides intrinsic spatial layout because of the continuous observation and smooth vehicle motion. Moreover, by capturing the trajectory of pedestrians upon their moving legs in motion profile, we can robustly distinguish pedestrian in motion against smooth background. The experimental results of streaming data collected from various sensors including camera and LiDAR demonstrate that, in the reduced temporal-to-spatial space, an effective recognition of driving scene can be learned through Semantic Segmentation. The second contribution of this work is that it accommodates standard semantic segmentation to sequential semantic segmentation network (SE3), which is implemented as a new benchmark for image and video segmentation. As most state-of-the-art methods are greedy for accuracy by designing complex structures at expense of memory use, which makes trained models heavily depend on GPUs and thus not applicable to real-time inference. Without accuracy loss, this work enables image segmentation at the minimum memory. Specifically, instead of predicting for image patch, SE3 generates output along with line scanning. By pinpointing the memory associated with the input line at each neural layer in the network, it preserves the same receptive field as patch size but saved the computation in the overlapped regions during network shifting. Generally, SE3 applies to most of the current backbone models in image segmentation, and furthers the inference by fusing temporal information without increasing computation complexity for video semantic segmentation. Thus, it achieves 3D association over long-range while under the computation of 2D setting. This will facilitate inference of semantic segmentation on light-weighted devices. The third application is speed and path planning based on the sensing results from naturalistic driving videos. To avoid collision in a close range and navigate a vehicle in middle and far ranges, several RP/MPs are scanned continuously from different depths for vehicle path planning. The semantic segmentation of RP/MP is further extended to multi-depths for path and speed planning according to the sensed headway and lane position. We conduct experiments on profiles of different sensing depths and build up a smoothly planning framework according to their them. We also build an initial dataset of road and motion profiles with semantic labels from long HD driving videos. The dataset is published as additional contribution to the future work in computer vision and autonomous driving.

Imaging and computer vision systems deployed in real-world environments face the challenge of accommodating a wide range of lighting conditions. However, the cost, the demand for high resolution, and the miniaturization of imaging devices impose physical constraints on sensor design, limiting both the dynamic range and effective aperture size of each pixel. Consequently, conventional CMOS sensors fail to deliver satisfactory capture in high dynamic range scenes or under photon-limited conditions, thereby impacting the performance of downstream vision tasks. In this thesis, we address two key problems: 1) exploring the utilization of spatial multiplexing, specifically spatially varying exposure tiling, to extend sensor dynamic range and optimize scene capture, and 2) developing techniques to enhance the robustness of object detection systems under photon-limited conditions. In addition to challenges imposed by natural environments, real-world vision systems are susceptible to adversarial attacks in the form of artificially added digital content. Therefore, this thesis presents a comprehensive pipeline for constructing a robust and scalable system to counter such attacks.

In the automatic classification of colored natural textures, the idea of proposing methods that reflect human perception arouses the enthusiasm of researchers in the field of image processing and computer vision. Therefore, the color space and the methods of analysis of color and texture, must be discriminating to correspond to the human vision. Rock images are a typical example of natural images and their analysis is of major importance in the rock industry. In this paper, we combine the statistical (Local Binary Pattern (LBP) with Hue Saturation Value (HSV) and Red Green Blue (RGB) color spaces fusion) and frequency (Gabor filter and Discrete Cosine Transform (DCT)) descriptors named respectively Gabor Adjacent Local Binary Pattern Color Space Fusion (G-ALBPCSF) and DCT Adjacent Local Binary Pattern Color Space Fusion (D-ALBPCSF) for the extraction of visual textural and colorimetric features from direct view images of rocks. The textural images from the two G-ALBPCSF and D-ALBPCSF approaches are evaluated through similarity metrics such as Chi2 and the intersection of histograms that we have adapted to color histograms. The results obtained allowed us to highlight the discrimination of the rock classes. The proposed extraction method provides better classification results for various direct view rock texture images. Then it is validated by a confusion matrix giving a low error rate of 0.8% of classification.

Wi-Fi fingerprint-based indoor localization is one of the most practical localization methods, which does not require extra infrastructure and special hardware. However, we need to acquire a dataset with a high-density dataset in the target environment in this framework. To overcome the data acquisition cost problem, we propose a brand new data augmentation for Wi-Fi indoor localization named Between-Location data augmentation (BL data augmentation). We generate the fingerprint data for the whole target environment with high density by only using the sparsely sampled data. Between-Class learning, which is the origin of BL data augmentation and the latest powerful data augmentation method for sound recognition and image processing, mixes two data linearly with normalization; however, this mixing does not make sense in indoor localization because mixed fingerprint has no meaning and the label of indoor localization is not categorical information but physically correlated information. To overcome these two problems, we propose the generative model based on neural networks installed the physical relationship of labels and Wi-Fi fingerprint property. BL data augmentation enables us to reduce data sampled locations while keeping the localization accuracy even if some target locations have no data. From the experimental results, indoor localization methods with BL data augmentation outperform the state-of-the-art data augmentation method on several indoor localization models, whatever the data collection location is dense or sparse. Moreover, the localization with BL data augmentation using 10 % sampled location achieves the same accuracy with localization without data augmentation using all sampled locations.

Recently, electrocardiogram (ECG) signals have received a high level of attention as a physiological signal in the field of biometrics. It has presented great possibilities for its strength against counterfeit. However, the ECG feature templates are irreplaceable, and a compromised template implies a permanent loss of identity. Therefore, several studies have been introduced biometric template protection techniques such as cancelable techniques to protect the original template in case it is stolen or lost. In this research, a cancelable ECG approach is proposed to protect the ECG feature template for human authentication. In our system, we first employed some image processing techniques for preprocessing the input ECG signals. Then, a deep transfer learning approach is employed to extract the deep ECG features. Later, the proposed cancelable approach based on DNA and amino acid is applied to protect the deep feature templates. Lastly, a Support Vector Machine (SVM) is employed for authentication. Extensive experiments on two commonly used datasets coupled with comprehensive theoretical analysis demonstrate the highest accuracy of the proposed system and the strong resilience of the system to various security and privacy attacks. Results show that the proposed cancelable method meets all requirements of cancelable biometrics such as irreversibility, revocability, and unlinkability.

Smart wheelchairs (SW) technology is one of the solutions to help disabled people who do not have a hand or people to help them. Apart from able to move on its own, a smart wheelchair needs to be safe to use. One of the ways to increase SW safety is the ability to detect obstacles. In this study, we tried to create obstacle detection that can classify the stairs descent and floor based on image processing. To achieve our purpose, Contrast Limited Adaptive Histogram Equalization (CLAHE) is used to increase image contrast. After that, Gray Level Co-occurrence Matrix (GLCM) is used to extract features from the image. Finally, Back Propagation Neural Network (BPNN) is used to classify the image. Based on the test result, BPNN achieves results with 95% Accuracy, 95% Sensitivity, 95% Specificity with an average computation time of 0.0035 s.

Traditional fault diagnosis methods are easy to be affected by different working conditions. This paper proposed a motor fault diagnosis method based on visual knowledge, to reduce the impact of changes in working conditions and improve the feature extraction ability. The mapping relationship between actual faults and image intuitive features by symmetrized dot pattern (SDP) and scale invariant feature transform (SIFT) is established in this paper. The fault state is obtained by statistics of the matching point with the dictionary templates generated from signals of normal and unnormal motors. Compared with other machine learning algorithms, this method does not need too much data training and learning. The efficiency of this method is validated by experiments, and the data image processing technology has great industrial application value in the field of motor fault detection or monitoring in the age of intelligence.

As we know, the fractal theory is an effective method for irregular image processing and analysis, which is difficult to implement using other baseline methods. However, Extreme Learning Machine (ELM) algorithm in combination with fractal theory can provide a better solution than the single fractal theory in image processing, transformation, data prediction, and so on. The features including fractal dimension, area ratio, and average perimeter of hematite, magnetite, calcium silicate, calcium ferrite, and stomata in the microstructure of irregular pellet images are extracted by artificial intelligence (AI) technologies. An AL-based ELM model suitable for the features of pellet images was constructed, the ELM model was optimized by regularization, and the feature parameters of pellet images were predicted by improved ELM algorithm, the optimal number of neuron nodes in the hidden layer was obtained for every mineral. The results show that the efficiency of model training and prediction in the feature for irregular pellet images is highly comparable to baseline methods. The method can be used as a reference in the intelligent prediction, control, and optimization of pellet image quality.

Change detection is a key technology in the field of polarimetric synthetic aperture radar (PolSAR) image processing. The current research on the change detection mainly focuses on studying PolSAR images with the same angle or small angle difference, and the angle problem is not considered. However, when the angle difference occurs, especially a large angle difference, some pixels might be falsely detected because the angle difference can affect the polarimetric characteristics. In this letter, we propose a multilevel information fusion-based (MIFB) method, which is suitable for extracting change information from PolSAR images with angle difference. In particular, the proposed method first adopts data resolution correction, then applies an improved feature-based registration algorithm, and finally, incorporates weighted graph theory with the superpixel segmentation algorithm to extract and merge pixel-based and object-based change areas to eliminate false alarms. Experimental results for multitemporal and multiangle PolSAR images reveal that the MIFB method can effectively eliminate false detection caused by angle differences and improve the detection accuracy.

Person Re-IDentification (ReID) aims at re-identifying persons from different viewpoints across multiple cameras. Capturing the fine-grained appearance differences is often the key to accurate person ReID, because many identities can be differentiated only when looking into these fine-grained differences. However, most state-of-the-art person ReID approaches, typically driven by a triplet loss, fail to effectively learn the fine-grained features as they are focused more on differentiating large appearance differences. To address this issue, we introduce a novel pairwise loss function that enables ReID models to learn the fine-grained features by adaptively enforcing an exponential penalization on the images of small differences and a bounded penalization on the images of large differences. The proposed loss is generic and can be used as a plugin to replace the triplet loss to significantly enhance different types of state-of-the-art approaches. Experimental results on four benchmark datasets show that the proposed loss substantially outperforms a number of popular loss functions by large margins; and it also enables significantly improved data efficiency.

The outbreak of COVID-19 affected global nations and is posing serious challenges to healthcare systems across the globe. Radiologists use X-Rays or Computed Tomography (CT) images to confirm the presence of COVID-19. So, image processing techniques play an important role in diagnostic procedures and it helps the healthcare professionals during critical times. The current research work introduces Multi-objective Black Widow Optimization (MBWO)-based Convolutional Neural Network i.e., MBWO-CNN technique for diagnosis and classification of COVID-19. MBWO-CNN model involves four steps such as preprocessing, feature extraction, parameter tuning, and classification. In the beginning, the input images undergo preprocessing followed by CNN-based feature extraction. Then, Multi-objective Black Widow Optimization (MBWO) technique is applied to fine tune the hyperparameters of CNN. Finally, Extreme Learning Machine with autoencoder (ELM-AE) is applied as a classifier to confirm the presence of COVID-19 and classify the disease under different class labels. The proposed MBWO-CNN model was validated experimentally and the results obtained were compared with the results achieved by existing techniques. The experimental results ensured the superior results of the ELM-AE model by attaining maximum classification performance with the accuracy of 96.43%. The effectiveness of the technique is proved through promising results and the model can be applied in diagnosis and classification of COVID-19. © 2021 Tech Science Press. All rights reserved.

The accuracy of the magnetic resonance (MR) image diagnosis depends on the quality of the image, which degrades mainly due to noise and artifacts. The noise is introduced because of erroneous imaging environment or distortion in the transmission system. Therefore, denoising methods play an important role in enhancing the image quality. However, a tradeoff between denoising and preserving the structural details is required. Most of the existing surveys are conducted on a specific MR image modality or on limited denoising schemes. In this context, a comprehensive review on different MR image denoising techniques is inevitable. This survey suggests a new direction in categorizing the MR image denoising techniques. The categorization of the different image models used in medical image processing serves as the basis of our classification. This study includes recent improvements on deep learning-based denoising methods alongwith important traditional MR image denoising methods. The major challenges and their scope of improvement are also discussed. Further, many more evaluation indices are considered for a fair comparison. An elaborate discussion on selecting appropriate method and evaluation metric as per the kind of data is presented. This study may encourage researchers for further work in this domain.

Brain tumors used to be uncommon, but they are increasingly becoming more common. Magnetic Resonance Images (MRI) scans may also be used by the medical specialist to detect brain malignancies. One of the most critical concerns in artificial intelligence systems is medical diagnosis via image processing and machine learning. Artificial intelligence based machine learning has enabled the digitalized the process of health monitoring. Diagnostic Images are a valuable source of information for determining the prognosis and treatment of certain cancers. It takes shape when human cells do not develop, split, or perish in the same way as conventional cells do. All voluntary and involuntary actions in the human body are controlled by the brain. Maintaining a healthy brain is critical for living a longer life. This paper proposes brain tumor detection using modified particle swarm optimization (MPSO) segmentation with ensemble classification. Initially image noise is suppressed using wiener filter. Then the feature extraction process is implemented using Haralick features. The SVM classifier with improved fuzzy segmentation is compared to the proposed work. With an accuracy of 98.2 percent, the new model outperformed the previous model.

Automatic classification of the plants is growing area of association with computer science and Botany, it has attracted many researchers to subsidize plant classification using image processing and machine learning techniques. Plants can be classified using number of traits such as leaf color, flowers, leaves, roots, leaf shape, leaf size etc. highly depends upon feature selection methods. However extraction of features from selected trait is most significant state in classification. State-of-the-art classification can be achieved by using leaf characteristics such as leaf venation patterns, leaf spectral signatures, leaf color, leaf shape, etc. This paper describes multimodal plant classification system using leaf venation patterns and its spectral signatures as a significant features. This paper shows that the feature fusion can be used to achieve efficient plant identification. The accuracy of identification for leaf spectral data, leaf venation features and HOG features is validated, it signifies that feature fusion technique performs better than that of non-imaging spectral signatures features only, with recognition result of 98.03% GAR and 93.51% GAR, respectively.

Anomaly detection (AD) is a field of intense research in remote sensing (RS) image processing. Identifying low probability events in RS images is a challenging problem given the high dimensionality of the data, especially when no (or little) information about the anomaly is available a priori. While a plenty of methods are available, the vast majority of them do not scale well to large datasets and require the choice of some (very often critical) hyperparameters. Therefore, unsupervised and computationally efficient detection methods become strictly necessary, especially now with the data deluge problem. In this article, we propose an unsupervised method for detecting anomalies and changes in RS images by means of a multivariate Gaussianization methodology that allows to estimate multivariate densities accurately, a long-standing problem in statistics, and machine learning. The methodology transforms arbitrarily complex multivariate data into a multivariate Gaussian distribution. Since the transformation is differentiable, by applying the change of variables formula, one can estimate the probability at any point of the original domain. The assumption is straightforward: pixels with low estimated probability are considered anomalies. Our method can describe any multivariate distribution, makes an efficient use of memory and computational resources, and is parameter-free. We show the efficiency of the method in experiments involving both AD and change detection (CD) in different RS image sets. For AD, we propose two approaches. The first is using directly the Gaussianization transform and the second is using a hybrid model that combines Gaussianization and the Reed-Xiaoli (RX) method typically used in AD. For CD, we take advantage of the Gaussianization transform and attribute the change to pixels with low probability compared to the first image, instead of those with high difference value typically employed in RS. Results show that our approach outperforms other linear and nonlinear methods in terms of detection power in both anomaly and CD scenarios, showing robustness and scalability to dimensionality and sample sizes.

In recent days, facial emotion recognition techniques are considered important and critical due wide array of application domains use facial emotion as part of their workflow and analytics gathering. Reduced recognition rate, inefficient computation and increased time consumption are the major drawbacks of these techniques. To overcome these issues, this paper develops the new facial emotion recognition technique named as Minimal Angular Feature Oriented Neural Network based Emotion Prediction (MAFONN-EP). Initially, the input video sequence are categorized into image frames that are pre-processed by eliminating the noise by using Weighted Median Filtering (WMF) technique and to separate the background and foreground regions using Edge Preserved Background Separation and Foreground Extraction (EPBSFE) technique. Then, the set of texture patterns are extracted based on four key parts such as two eyes, nose and mouth by using the Minimal Angular Deviation (MAD) technique. Particular features are selected by employing the Cuckoo Search based Particle Swarm Optimization (CS-PSO) technique that also reduces the feature dimensionality. Finally, the Weight Based Pointing Kernel Classification (WBPKC) technique is employed for recognizing the emotion. In the experimental results, the performance of the proposed technique is analyzed and compared with different performance measures like accuracy, sensitivity, specificity, precision, recall.

Compared with the synthetic aperture radar (SAR) image processing theory based on local neighborhood, the nonlocal theory is not limited to a local neighborhood of an image and has great potential in change detection of SAR images. In this study, an approach using ratio-based nonlocal information (RNLI) is proposed for change detection in multitemporal SAR images. First, the RNLI is extracted from a spatial-temporal nonlocal neighborhood where the similarity of two pixels in the nonlocal neighborhood is well characterized by the proposed ratio-based Gaussian kernel function. The parameters of RNLI: noise level and matching window size are adaptively determined to avoid the uncertainty of the change detection result caused by user experience. Second, the difference image is generated by using the RNLI and the ratio operator. Finally, the change map is obtained by segmenting the difference image with a threshold. Experiments conducted on two real datasets and two simulated datasets showed that the proposed method performed better than the other advanced change detection methods, which can better retain the edge information of the changed area while reducing the overall error of the change detection results.

Corrosion phenomena are usually difficult to recognize without a deep knowledge of the electrochemical properties of materials, this creates difficulties in the analysis of corrosion in practice, control measures are developed through image processing to solve these problems. This article describes a methodology for the analysis of the inner surface of steam pipelines by means of digital image processing (DIP). A classification algorithm is presented that is able to detect four levels of corrosion on the inner surface of steam pipelines. Gray-level co-occurrence matrix GLCM, which analyzes all the attributes of each image texture was employed. The performance of the classification algorithm was evaluated by using a confusion matrix, which showed very reliable classification results by comparing with experimental tests.

In medical science, information technology plays a main role in image processing for medicinal investigation and classification. For this reason “Magnetic Resonance Imaging” (MRI) can be useful today in the medical world which in turn is used to generate a comprehensive picture of the body's soft tissue and bones. The suggested technique utilizes an effective technique for brain tumor segmentation and classification. To segment and classify the brain tumor MR image by Modified fuzzy c means clustering (MFCM) and Artificial Neural Network (ANN). From the input image the proposed method extracts the shape, intensity and texture features. Here the extracted features are optimally selected by means of Hybrid Fruit fly and artificial bee colony (HFFABC). Both the segmentation and classification performance of the implemented technique is estimated in terms of “Accuracy, Sensitivity, Specificity, Ppv, Npv, Fpr And Fnr”. The implementation result shows the efficiency of proposed tumor segmentation and classification technique in segmenting the tissues perfectly from the MRI images of human nervous system. The classification performance of the implemented techniques is evaluated in terms of accuracy, sensitivity and specificity. The implementation results show the sensitivity, specificity & efficiency as 98.1%, 99.8% and 99.59%respectively.

Band selection has been proven to be effective in reducing the dimensionality of the hyperspectral image by finding the most distinctive and informative bands. An essential operation for band selection is to quantify band similarity using metrics, such as entropy and mutual information. For the first time, we proposed that this quantification can also be conducted by borrowing the core ideas from landscape ecology, namely employing landscape metrics. To validate this proposal, we first developed a joint landscape metric and error image approach to quantify the similarity between two bands. Using the quantified similarity and Boltzmann entropy-based information content, we then proposed an efficient priority-based band selection algorithm to search optimal bands. To evaluate the proposed approach, we carried out a comprehensive evaluation involving 80 possible landscape metrics, two methods for quantifying band similarity, four classifiers, and four state-of-the-art, popular approaches as the benchmark. Extensive experimental results demonstrated that the proposed approach exhibited global superiority over these benchmark approaches using all these classifiers. We also found that the best choices of landscape metrics to implement the proposed approach came from the following two categories of metrics: aggregation and diversity. Although this letter presents the first study of its kind in employing landscape metrics for unsupervised band selection, it indicated that landscape metrics might open a door for metric-based approaches for image processing, including band selection.

Image processing via convolutional neural network (CNN) has been developed rapidly for remote sensing technology. Moreover, techniques for accurately extracting building footprints from remote sensed images have attracted considerable interest owing to their wide variety of common applications, including monitoring natural disasters and urban development. Extraction of building footprints can be performed easily by semantic segmentation using U-Net-like CNN architectures. However, obtaining precise boundaries of segmentation masks remains challenging due to various impediments surrounding target objects. In this study, we propose a method to elaborate edges of buildings detected in remote sensed images to enhance the boundaries of segmentation masks. The proposed method adopts holistically nested edge detection (HED), which extracts edge features at an encoder of a given architecture. In the proposed boundary enhancement (BE) module, an extracted edge and segmentation mask are combined, sharing mutual information. To enable the proposed method efficiently to adapt to a wide variety of conditions, we design a distinctive approach adopting a HED unit and BE module, which is applicable to various semantic segmentation networks containing encoder-decoder structures. Experiments were conducted on five different datasets (DeepGlobe, Urban3D, WHU [high-resolution (HR), low-resolution (LR)], and Massachusetts). The results demonstrate that our proposed approaches improved on the performance of prior methods for extracting building footprints. Comparative experiments were conducted on various backbone architectures including U-Net, ResUNet++, TernausNet, and U-shape spatial pyramid pooling (USPP) to ensure the effectiveness of the proposed method. Based on various evaluation metrics and qualitative analysis, our results show that the proposed method achieved improved performance compared with prior methods for all datasets and backbone networks.

A novel spatial singularity-exponent-domain multiresolution imaging (SSMRI) method is proposed in this article. It is aimed at improving the image processing ability for the single-channel synthetic aperture radar (SAR), thereby acquiring the robust image feature for SAR target detection at the very low SNR. Combining the 2-D singularity power spectrum (SPS) and the 2-D pseudo-Wigner-Ville distribution (PWVD), the SSMRI method is derived. Consequently, the single-channel SAR images are transformed to obtain spatial multiresolution SAR images with respect to the singularity exponent. Furthermore, the separability of the SAR image target in the space of the singularity exponent is analyzed, and the separability theorem in the sense of SSMRI is proved. In particular, under the background of GWN and fractal noise, the separability of SAR image targets based on SSMRI processing is studied. In addition, the stability and robustness of SSMRI-SAR feature extraction are demonstrated. On this basis, a maritime SAR ship target detection method based on SSMRI is put forward in the extremely low SNR condition. The experiment results on the SAR-Ship-Dataset indicate that the proposed method is superior in performance to the traditional CFAR or 2-D-SPS method. Especially when SNR =-30 dB, the detection performance with more than 99.4% can be achieved.

There are many pathogens in the reproductive system in both women and men, which are largely responsible for the death of thousands of women as a result of incorrect diagnosis and failure to treat diseases of the reproductive system such as uterine cancer, ectopic pregnancy, acute and chronic infections of the uterus and Fallopian tubes, puerperal infections, and in the event that the patient survived death. These diseases have bad effects, including infertility, miscarriage, fetal death, birth of low-weight fetuses, fetal blindness, pneumonia, and mental retardation. These diseases are transmitted through the mucous membranes during vaginal, anal, or oral intercourse with a person who is infected or passed from mother to fetus. Wrong sexual behaviors also lead to the acquisition of genital infections. The incidence of reproductive system diseases in women is 50%, especially at an early age, compared to 25% for men, and affects them more severely. Accordingtostudies,two-thirdsofcasesofsexuallytransmitteddiseasesareobtainedintheirteensortwenties. There is limited access to health care for women infected with these diseases in developing countries, as health care isoftenprovidedinthesecountriesthrougharangeofservicesforindividuals,familyplanningclinics,reproductive healthcenters,andpublichospitals.However,indevelopingcountries,untrainedpeopleprovidetreatmentwithout accurate diagnosis of the disease, which increases the exacerbation of sexually transmitted diseases, whereas the situation is much better in developed countries.

High spatial and spectral resolution (H2) imagery collected by unmanned aerial vehicle (UAV) systems is an important data source for precise crop classification. Although this data source can provide us with abundant information about the crops of interest, it also introduces new challenges for the image processing. Specifically, the spectral similarities of green crops lead to small inter-class distances, and the severe intra-class spectral variability and high spatial heterogeneity in H2 imagery increases the difficulty of precise classification. In addition, the scales of the different crop plots can show great differences, which makes it difficult to determine the optimal patch size for deep learning based classification models. In this paper, a spectral-spatial-scale attention network (S3ANet) is proposed for H2 imagery based precise crop classification. In the proposed method, each channel, each pixel, and each scale perception of the feature map is adaptively weighted to relieve the intra-class spectral variability, the spatial heterogeneity, and the scale difference of the crop plots, respectively. Furthermore, the proposed S3ANet method introduces the additive angular margin loss function to further increase the inter-class distances between the different crops, and reduce the misclassification effect. S3ANet was verified using the public WHU-Hi UAV-borne hyperspectral dataset and the new WHU-Hi-JiaYu dataset, which is a dataset for precise rice classification that was built by the authors. In these experiments, the overall accuracy of the proposed S3ANet method all exceeds 96% under 50 training pixels per class, and it achieved significant improvement compared with some state-of-the-art hyperspectral images classifiers (such as SSRN, CNNCRF and FPGA, etc.). The code of S3ANet is available at http://rsidea.whu.edu.cn/resource_sharing.htm .

Detection of cavitation in centrifugal pumps is critical in their condition monitoring. In order to detect cavitation more accurately and confidently, more advanced signal processing techniques are needed. For the classification of a pump conditions based on the outputs of these techniques, advanced machine learning techniques are needed. In this research, an automatic system for cavitation detection is proposed based on machine learning. Bispectral analysis is used for analyzing the vibration signals. The resulting bispectrum images are given to convolutional neural networks (CNNs) as inputs. The CNNs are a pretrained AlexNet and a pretrained GoogleNet, which are used in this application through transfer learning. On the contrary, a laboratory test setup is used for generating controlled cavitation in a centrifugal pump. The suggested algorithm is implemented on the vibration dataset acquired from the laboratory pump test setup. The results show that the cavitation state of the pump can be detected accurately using this system without any need to image processing or feature extraction.

In laser keyhole welding processes, the dynamic behavior of the keyhole and molten pool is associated with the penetration state. In this paper, a deep learning-based monitoring system is employed to monitor the penetration state by inspecting the keyhole and molten pool. An image processing method based on parabola template and half molten pool is proposed to extract the boundary contour of the molten pool, which can effectively reduce the interference of metal vapor plume. 12 kinds of morphological features of the keyhole and molten pool are defined and extracted, especially 6 molten pool tail features. A data processing method is proposed to reduce the amount of data by 4/5 to avoid overfitting and remove abnormal data. The 12 variance features obtained through data processing can effectively increase the feature depth and improve the monitoring accuracy. A deep learning framework based on deep belief network (DBN) is established to model the relationship between the 24 features and their corresponding penetration states. The proposed framework achieves higher accuracy and stronger robustness in monitoring penetration states by comparing with the backpropagation neural network, support vector machine, decision tree, k-nearest neighbors and random forest. The results show that this proposed monitoring method can accurately and quickly judge the penetration state according to the keyhole and molten pool images obtained by the on-line monitoring system.

This work aims at automatically tracking the weld pool boundary to monitor the process and collect operation and process data for analysis and modeling of the operator. The strong arc radiation and less predictable operation add challenges. It is relatively difficult to design a static feature pattern to consistently detect the weld pool boundary/position under different welding conditions. A deep learning network, such as a conventional neural network (CNN), could provide a solution. However, its training requires large amount of data. In a classification problem where each image corresponds to one label, an automated method may be available to calculate the needed labels. Unfortunately, for the problem of image segmentation being addressed in this study, i.e., detecting the weld pool, the labels cannot be generated automatically or the problem would have been solvable by conventional image processing. An effective deep learning approach that does not require large datasets is needed. As such, we propose to use an architecture of the U-Net, which extracts contextual information by combining low-level feature maps with high-levels. It not only can be trained end-to-end from few images to perform well but is also known for its capability to be real-time. To train the network, various welding experiments have been conducted by randomly changing the welding current and welding speed. Various weld pool boundaries/shapes are generated under various welding conditions. As such, the data is representative to better ensure the reliability and robustness of the trained network. Experimental results verified that the trained network can detect the weld pool boundary under various conditions accurately in different welding current, welding speed, and weld pool shape.

Three-dimensional (3D) face application has attracted significant attention the field of multimedia and image processing. However, the end-to-end 3D face reconstruction method is still immature, and there are some problems, such as overfitting caused by too few training sets and unacceptable 3D face texture alignment performance. Therefore, we design a novel approach to construct a 3D face, named multi-objective evolutionary 3D face reconstruction based on improved encoder–decoder network (MoEDN). This study introduces a regularization algorithm named feature map distortion (Disout); whose purpose is to strengthen the network generalization ability . Based on this, we construct a multi-objective evolutionary 3D face reconstruction model, in which decision variables are distortion probability, distorted block size, distorted intensity, probability step, and learning rate; and objective functions are loss and structural similarity (SSIM). We use four multi-objective evolutionary algorithms (NSGA-II, AGEII, NSLS, and MOEA/D) to optimize the proposed model. Experimental results demonstrate that NSLS has the best performance. In addition, compared with position map regression network (PRNet), 2D-assisted self-supervised learning (2DASL) and other state-of-the-art, the proposed model achieves better loss values and NME values. Therefore, the proposed multi-objective evolutionary 3D face reconstruction model has outstanding 3D facial reconstruction performance in large poses and face expression.

Leukemia is usually diagnosed by viewing the smears of blood and bone marrow using microscopes and complex Cytochemical tests can be used to authorize and classify leukemia. But these methods are costly, slow and affected by the proficiency and expertise of the specialists concerned. Leukemia can be detected with the help of image processing-based methods by analyzing microscopic smear images to detect the presence of leukemic cells and such techniques are simple, fast, cheap and not biased by the specialists. The proposed study presents a computer aided diagnosis system that uses pretrained deep Convolutional Neural Networks (CNNs) for detection of leukemia images against normal images. The use of pretrained networks is comparatively an easy method of applying deep learning for image analysis and the comparison results of the present study can be used to choose appropriate networks for diagnostic tasks. The microscopic images used in the proposed work were downloaded from a public dataset ALL-IDB. In the proposed work, image classification is done without using any image segregation and feature extraction practices and the study used pretrained series network AlexNet, VGG-16, VGG-19, Directed Acyclic Graph (DAG) networks GoogLeNet, Inceptionv3, MobileNet-v2, Xception, DenseNet-201, Inception-ResNet-v2 and residual networks ResNet-18, ResNet-50 and ResNet-101 for performing the classification and comparison. A classification accuracy of 100% is obtained with all the pretrained networks used in the study for ALL_IDB1 dataset and for ALL_IDB2 dataset, 100% accuracy is obtained with all networks except the AlexNet and VGG-16. The efficacy of three optimization algorithms Stochastic Gradient Descent with Momentum (SGDM), Root Mean Square propagation (RMSprop) and Adaptive Moment estimation (ADAM) is also compared in all the classifications performed. The study considered the detection of leukemia in general only, and classification of leukemia into different types can be attempted as a future work.

Face expression recognition has been proved as a challenging task in image processing. Many related works on facial expression recognition had done but they faced several challenges during the classification of data with the stored database. It carried out various workflows on improvisation of classifiers based on deep learning but they have been lagging in understanding facial expression mainly because of disastrous forgetting, time management, data mixing, and data overfitting, etc. Ignoring all these challenges would lead to inaccurate recognition of facial expressions. Hence to overcome all the above issues this work proposed a model named adaptive increasing-margin adversarial neural iterative model involves triple threat filtration techniques along with modified scaling density-based spatial clustering of applications with noise and dual feature model for obtaining a better quality featured image. Advance back propagation artificial neural network model is initiated to overcome catastrophic forgetting, underfitting of data, over fitting of data, etc. Thus, the proposed work achieves better efficiency as well as high accuracy in terms of facial expression recognition.

The COVID-19 pandemic creates a worldwide threat to human health, medical practitioners, social structures, and finance sectors. The coronavirus epidemic has a significant impact on people's health, survival, employment, and financial crises; while also having noticeable harmful effects on our environment in a short span of time. In this context, the complexity of the Corona Virus transmission is estimated and analyzed by the measure of non-linearity called the Generalized Fractal Dimensions (GFD) on the chest X-Ray images. Grayscale image is considered as the most important suitable tool in the medical image processing. Particularly, COVID-19 affects the human lungs vigorously within a few days. It is a very challenging task to differentiate the COVID-19 infections from the various respiratory diseases represented in this study. The multifractal dimension measure is calculated for the original, noisy and denoised images to estimate the robustness of COVID-19 and other noticeable diseases. Also the comparison of COVID-19 X-Ray images is performed graphically with the images of healthy and other diseases to state the level of complexity of diseases in terms of GFD curves. In addition, the Mean Absolute Error (MAE) and the Peak Signal-to-Noise Ratio (PSNR) are used to evaluate the performance of the denoising process involved in the proposed comparative analysis of the representative grayscale images.