Search

Computer vision has arisen as one of the most important application areas in manufacturing processes. This work shows a new real-time texture analysis for medium-density fiberboard with melamine paper, using edge detection techniques and threshold detection methods. To minimize the time of identification of defects, the images of fiberboard are sent to a grid system. In a first phase, several tests are carried out using different image resolutions and sizes. In a second phase, to optimize the system, with the best resolution obtained and using a grid system, our aim is to minimize the time of detection of possible defects without jeopardizing the performance of the quality control system. Results show that, using accurate resolutions, the error detection process is quicker and the defect identification rate significantly improves. [ABSTRACT FROM AUTHOR]

Methods for (PC) quality assessment customarily perform local comparisons between corresponding points in the "degraded" and pristine PCs. These methods often compare the geometry of the degraded PC and the geometry of the reference PC. More recently, a few methods that use texture information to assess the PC quality have been proposed. In this work, we propose a full-reference Point Cloud Quality Assessment (PCQA) metric that combines both geometry and texture information to provide an estimate of the PC quality. We use a projection technique that represents PCs as 2D manifolds in the 3D space. This technique maps attributes from the PCs onto the folded 2D grid, generating a pure-texture 2D image (texture maps) that contains PC texture information. Then, we extract statistical features from these texture maps using a multi-scale rotation-invariant texture descriptor named the Dominant Rotated Local Binary Pattern (DRLBP). The texture similarity is computed by measuring the statistical differences between reference and test PCs. The geometrical similarities are computed using geometry-only distances. Finally, the texture and geometrical similarities are fused using a stacked regressor to model the PC visual quality. Experimental results show that the proposed method outperforms several state-of-the-art methods. An implementation of the metric described in this paper can be found at https://gitlab.com/gpds-unb/pc-gats-metric. [ABSTRACT FROM AUTHOR]

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Single-image super-resolution reconstruction technology is to reconstruct fuzzy low-resolution images into clearer high-resolution images. It is a research hotspot in the field of computer vision and image processing. In recent years, the attention mechanism has been successfully applied in image super-resolution reconstruction. However, the existing methods use the channel attention mechanism and the spatial attention mechanism separately, or simply superimpose them, which cannot effectively unify the adjustment effects of both, and the performance is limited. This paper proposes a method that can merge channel attention and spatial attention into pixel attention, which achieves more precise adjustment of feature map information. The pixel attention convolutional neural network method built on this basis can improve the quality of image texture detail reconstruction. We have been tested on five widely used standard datasets, the experimental results show that the method is superior to most current representative reconstruction methods, especially in terms of high-definition picture texture restoration. [ABSTRACT FROM AUTHOR]

Most of the plant diseases severely affect the plant leaves and thus can be identified from infected leaf images using modern computer vision techniques. During the last decade, various machine learning methods have been developed to detect and analyze plant leaf disease accurately. Hence, developing an effective machine learning prediction method for plant disease identification at an early stage arises enormous interest in computer vision research. Diagnosing plant leaf diseases is a challenging area of research, mainly because leaf images exhibit complexity arising from irregular shapes, uneven colors, a mixture of normal and abnormal regions, and are often accompanied by complex backgrounds. In this paper, a new feature descriptor titled as the local triangular-ternary pattern (LTriTP) for plant leaf disease detection is proposed. The proposed method extracts feature vectors using the triangular shape descriptor to enable efficient extraction and representation of features from the leaf images. To apply the ternary pattern, an absolute mean value based dynamic threshold is computed, which supports the sensitive analysis of plant leaf image texture information by producing highly relevant and diverse values. Since plant disease can appear at any orientation on a leaf image, therefore in each triangle, a histogram of the gradient is also computed in four directions (00, 450, 900, and 1350) to find the gradient change of infected regions in contrast to healthy areas. This is what we termed as the triangular histogram of gradient (T-HOG), which makes the proposed method orientation invariant. Fusion of T-HOG and LTriTP features has shown better disease detection performance. Multimodal classification is performed using 6 disease classes of tomato leaf images. The performance of the proposed method is compared with renowned methods like Local Binary Pattern, and Local Ternary Pattern using the publicly available PlantVillage dataset of tomato images. The classification accuracy varies from 94.50% to 97.80% with respect to different classifiers, where the error rate varies from 2.03% to 5.03%. [ABSTRACT FROM AUTHOR]

Identifying locations of protein expression in live cells plays an important role in several medical applications ranging from early disease diagnosis to monitoring effectiveness of drugs. Protein localization is directly related to their cell types. Today florescence imaging is widely used to understand biology at the cellular level. Hence, cell phenotype classification in fluorescence microscope images, is related with protein localization. Today it is performed by human, which is very time consuming with low accuracy. According to the visual structure, it can be seen that samples of a unique cell type have quite similar texture, but the texture of different cell types, are very different. In this respect, texture information can be used more widely than shape or color information, to classify types. Local ternary pattern is a noise-resistant texture descriptor that provides discriminative features. In this paper a local texture analysis descriptor is proposed titled multi threshold uniform-based local ternary patterns with notation MT-ULTP. MT-ULTP extracts local significant texture information in different locality levels. In this respect, local ternary patterns are extracted in different thresholds and finally the occurrence probability of the uniform patterns is extracted as features. MT-ULTP is a skillful combination of LTP and MLBP with novelty in feature extracting and local pattern selecting. Performance of the proposed descriptor is evaluated on 2d-hela dataset in terms of accuracy. 2d-hela is the benchmark dataset of cell phenotype images. Experimental results show that MT-ULTP provides higher classification rates than very well-known texture descriptors such as lbp-like descriptors. In other experiments, it has been shown that ignoring uniform textural patterns in the image analysis can increase the accuracy of cell phenotype classification and some other computer vision-based applications. The results also showed that extraction uniform patterns based on a combination of thresholds provide better results than the simple form in local ternary patterns. The proposed image texture descriptor is a general case which can be used in many computer vision applications to describe the image contents. [ABSTRACT FROM AUTHOR]

A machine vision sensor was developed for predicting deviations from the optimum amount of pitch in anode formulations using paste texture analysis. It could help operators mitigate the impact of the increasing variability of anode raw materials (coke and pitch). Paste samples were formulated in the laboratory using dry aggregate mixes obtained using two cokes having different properties and various amounts of pitch. These were imaged, formed into small cylindrical anodes, and baked to measure their density. A combination of image texture methods was used for extracting relevant paste textural features. The latter were then used as inputs of partial least squares regression models to predict deviations from the maximum baked density. Good prediction results were obtained. Furthermore, the sensor was able to detect when the paste was at the optimal amount of pitch for both cokes and to measure deviations from it. [ABSTRACT FROM AUTHOR]

The human visual system unconsciously determines the color of the objects by "discounting" the effects of the illumination, whereas machine vision systems have difficulty performing this task. Color constancy algorithms assist computer vision pipelines by removing the effects of the illuminant, which in the end enables these pipelines to perform better on high-level vision tasks based on the color features of the scene. Due to its benefits, numerous color constancy algorithms have been developed, and existing techniques have been improved. Combining different strategies and investigating new methods might help us design simple yet effective algorithms. Thereupon, we present a color constancy algorithm based on the outcomes of our previous works. Our algorithm is built upon the biological findings that the human visual system might be discounting the illuminant based on the highest luminance patches and space-average color. We find the illuminant estimate based on the idea that if the world is gray on average, the deviation of the brightest pixels from the achromatic value should be caused by the illuminant. Our approach utilizes multi-scale operations by only considering the salient pixels. It relies on varying surface orientations by adopting a block-based approach. We show that our strategy outperforms learning-free algorithms and provides competitive results compared to the learning-based methods. Moreover, we demonstrate that using parts of our strategy can significantly improve the performance of several learning-free methods. We also briefly present an approach to transform our global color constancy method into a multi-illuminant color constancy approach. [ABSTRACT FROM AUTHOR]

Image restoration is a fundamental problem in computer vision, with the goal of restoring high-quality images from degraded low-quality observation images. However, the ill-posedness of restoration problem often leads to artifacts in the results. It inspires us to study the combination of prior, effectively restrict the solution space and improving the quality of the restored image. In this paper, a novel hybrid regularization method for image restoration is proposed, which adopts both internal and external image priors into a unified framework. Specifically, a new hybrid regularization model is designed. The TV model and a deep image denoiser are inserted into the restoration model using the plug-and-play framework, protecting image details while implicitly using external information for deep denoising. Moreover, in order to make the proposed hybrid regularization operable, an adaptive parameter method is proposed to adaptively balance the TV model and learned model in iteration. Experiments show that the proposed method surpasses the performance of existing image restoration techniques. [ABSTRACT FROM AUTHOR]

This paper presents a scheme for the representation and recognition of the dynamic texture in the noisy environment. Dynamic texture is the sequence of images of a moving scene that shows some form of temporal regularity. Though, the dynamic texture is the spatiotemporal extension of the conventional texture, its analysis requires additional attention, since the motion causes continuous changes in the geometry of these textures. Hence, to recognize the noisy dynamic texture, the noise should be estimated not only at the spatial level; it must also be estimated at the temporal level. To this end, an auto tuned noise resistance descriptor, based on the Local Binary Pattern approach, is proposed for the modeling and classification of the dynamic texture. Our approach based on the fact that, uniform local binary patterns are the fundamental units of image texture and occur more frequently in an image in comparison to non-uniform patterns. Noise affects these uniform local binary patterns and more likely fall into non-uniform codes. To counter this, we have extended conventional local binary pattern descriptor from a 2-value code to a 3-value code to include an additional state (called indecisive state) to represent the noise affected pixels. However, the estimation of the indecisive state is of the primary concern of this letter due to the inherently varying nature of the dynamic texture. The proposed technique devised a new scheme to estimate the noisy pixels in a dynamic texture. Eventually, the indecisive state is corrected back to non-noisy natural states using a mapping function so as to form a uniform LBP code. Experimental results on the UCLA and Dyntex++ databases demonstrate high classification efficiency of the proposed approach in the noisy environment. [ABSTRACT FROM AUTHOR]

With the continuous progress of science and technology, image processing techniques have been used increasingly in recent years. Image processing plays an indispensable role in the fields of computer vision, artificial intelligence, pattern recognition, and related fields. Improvements in basic algorithms and the development of new algorithms have resulted in considerable innovation and progress. This paper is devoted to finding new game applications in a branch of image processing. It introduces an analysis model proposed by the author and discusses the relationship between roughness in the frequency domain and visual image interpretation. By using the concept of roughness, we separated the image features into meaningful information and residual information and analysed the image in the frequency domain. The results were compared with those of traditional image processing methods. The starting point is the visual identification of a feature based on human interpretation. The image information was separated into meaningful features and the residual component to reduce the redundancy of the model. This allowed for a sparse representation of the feature information in the image. By analysing the meaningful features and residual components of an image separately, we established a relationship between the results and the original images. Parameters such as texture, morphology, and the degree of blurring were considered and we developed a parameter called "frequency roughness". The algorithm incorporates the concepts of frequency and roughness and the roughness is determined in the frequency domain. The frequency roughness algorithm successfully separated the rough features in the frequency domain and calculated the residual value in an image. This model provided more accurate image processing results than comparable methods. This paper includes an analysis and game applications of the proposed model for de-blurring, image enhancement, recognition, and other image processing tasks. Some game applications were successful, whereas others require further investigation. [ABSTRACT FROM AUTHOR]

Image deblurring is an essential problem in computer vision. Due to highly structured and special facial components (e.g. eyes), most general image deblurring methods and face deblurring methods failed to yield more explicit structure and facial details, resulting in too smooth, uncoordinated and distorted face structure. Considering the unique face texture and sufficient facial details, we present an effective face deblurring network by exploiting more regularized structure and enhanced texture information (RSETNet). We first incorporate the face parsing network with fine-tuning to obtain more accurate face structure, and we present the feature adaptive denormalization (FAD) to regularize the facial structure as a condition of auxiliary to generate more harmonious and undistorted face structure. Meanwhile, to improve the generated facial texture information, we propose a new Laplace depth-wise separable convolution (LDConv) and multi-patch discriminator. Compared with existing methods, our face deblurring method could restore face structure more accurately and with more facial details. Experiments on two public face datasets have demonstrated the effectiveness of our proposed methods in terms of qualitative and quantitative indicators. [ABSTRACT FROM AUTHOR]

In this paper, a new attempt has been made in the area of tool-based micromachining for automated, non-contact, and flexible prediction of quality responses such as average surface roughness ( R), tool wear ratio (TWR) and metal removal rate (MRR) of micro-turned miniaturized parts through a machine vision system (MVS) which is integrated with an adaptive neuro-fuzzy inference system (ANFIS). The images of machined surface grabbed by the MVS could be extracted using the algorithm developed in this work, to get the features of image texture [average gray level ( G)]. This work presents an area-based surface characterization technique which applies the basic light scattering principles used in other optimal optical measurement systems. These principles are applied in a novel fashion which is especially suitable for in-process prediction and control. The main objective of this study is to design an ANFIS for estimation of R, TWR, and MRR in micro-turning process. Cutting speed ( S), feed rate ( F), depth of cut ( D), G were taken as input parameters and R, TWR, MRR as the output parameters. The results obtained from the ANFIS model were compared with experimental values. It is found that the predicted values of the responses are in good agreement with the experimental values. [ABSTRACT FROM AUTHOR]

Siltation is a significant element that affects the efficiency and safety of water conveyance tunnels. One efficient inspection technique is optical vision inspection carried out by underwater robots. However, efficient processing is required to handle the volume of images that underwater robots collect. Convolutional neural networks (CNNs), have demonstrated considerable promise in computer vision, however it is challenging to implement these models in underwater robots. In this paper, we propose a classification framework for multiple siltation types based on siltation images of water conveyance tunnels using the structure-optimized MobileNet v3, namely SRNet. An underwater robotic image acquisition device is used to acquire the siltation images for training and testing. Out of 6000 images collected from 7 water conveyance tunnels, 4172 are used to train the proposed SRNet network. The remaining 1828 images are used to test it. Furthermore, multiple learning strategies are used to optimize the entire training process. Compared with other deep learning models, the proposed method shows great superiority in terms of recognition results, computational cost and model size. The proposed method effectively weighs model accuracy and complexity and can be used for rapid and accurate identification of siltation in water conveyance tunnel health monitoring. [ABSTRACT FROM AUTHOR]

In light of the prevalent issues concerning the mechanical grading of fresh tea leaves, characterized by high damage rates and poor accuracy, as well as the limited grading precision through the integration of machine vision and machine learning (ML) algorithms, this study presents an innovative approach for classifying the quality grade of fresh tea leaves. This approach leverages an integration of image recognition and deep learning (DL) algorithm to accurately classify tea leaves' grades by identifying distinct bud and leaf combinations. The method begins by acquiring separate images of orderly scattered and randomly stacked fresh tea leaves. These images undergo data augmentation techniques, such as rotation, flipping, and contrast adjustment, to form the scattered and stacked tea leaves datasets. Subsequently, the YOLOv8x model was enhanced by Space pyramid pooling improvements (SPPCSPC) and the concentration-based attention module (CBAM). The established YOLOv8x-SPPCSPC-CBAM model is evaluated by comparing it with popular DL models, including Faster R-CNN, YOLOv5x, and YOLOv8x. The experimental findings reveal that the YOLOv8x-SPPCSPC-CBAM model delivers the most impressive results. For the scattered tea leaves, the mean average precision, precision, recall, and number of images processed per second rates of 98.2%, 95.8%, 96.7%, and 2.77, respectively, while for stacked tea leaves, they are 99.1%, 99.1%, 97.7% and 2.35, respectively. This study provides a robust framework for accurately classifying the quality grade of fresh tea leaves. [ABSTRACT FROM AUTHOR]

Learning a one-shot domain adaptation model is an exciting and challenging topic in computer vision and graphics. A feasible solution is to fine-tune a pre-trained generator to the target domain by leveraging the powerful semantic capabilities of CLIP (Contrastive Language-Image Pretraining). Unfortunately, when the target image shows a significant difference from the source domain, existing methods would result in overfitting, and generated images do not correctly reflect the texture of the target image. To address this issue, we propose a Dynamic Domain Transfer Strategy (DDTS) to align the texture information between the source and target domain by dynamically adjusting the direction of domain transfer. Furthermore, the delicately designed dual-path hypernetworks of style and text (Dual-HyperST) for one-shot domain adaptation characterize the target domain's textual style and visual style with a text-guide path and a style-guide path. Specifically, the style-guided path predicts a set of style weight offsets by the target image, followed by the text-guided path predicts a set of text weight offsets by a text prompt. To better integrate the information between these two paths, we introduce a hypernetwork that learns to modulate the pre-trained generator instead of fine-tuning. Qualitative and quantitative experiments demonstrate the superiority of Dual-HyperST, which surpasses the state-of-the-art methods in the diversity and high quality of the generated images. [ABSTRACT FROM AUTHOR]

As robots have become more pervasive in our daily life, natural human-robot interaction (HRI) has had a positive impact on the development of robotics. Thus, there has been growing interest in the development of vision-based hand gesture recognition for HRI to bridge human-robot barriers. The aim is for interaction with robots to be as natural as that between individuals. Accordingly, incorporating hand gestures in HRI is a significant research area. Hand gestures can provide natural, intuitive, and creative methods for communicating with robots. This paper provides an analysis of hand gesture recognition using both monocular cameras and RGB-D cameras for this purpose. Specifically, the main process of visual gesture recognition includes data acquisition, hand gesture detection and segmentation, feature extraction and gesture classification, which are discussed in this paper. Experimental evaluations are also reviewed. Furthermore, algorithms of hand gesture recognition for human-robot interaction are examined in this study. In addition, the advances required for improvement in the present hand gesture recognition systems, which can be applied for effective and efficient human-robot interaction, are discussed. [ABSTRACT FROM AUTHOR]

This work proposes a GPU optimization methodology for real-time execution of ultra high frame rate applications with small frame sizes. While the use of GPUs for offline processing is well-established, real-time execution remains challenging due to the lack of real-time execution guarantees, especially for embedded GPUs. Our methodology introduces guidelines and a workflow by focusing on: (a) controlling latency by means of minimization of CPU-GPU interactions; (b) computation pruning; and (c) inter/intra-kernel optimizations. Furthermore, our approach takes advantage of multi-frame processing to attain significantly higher throughput at the cost of increased latency when the application permits such trade-offs. To evaluate our optimization methodology, we applied it to the monitoring and controlling of laser powder bed fusion machines, a widely used metal additive manufacturing technique. Results show that in the considered application, the required performance could be obtained on a Jetson Xavier AGX platform, and by sacrificing latency, significantly higher throughput was achieved. [ABSTRACT FROM AUTHOR]

Multi-view stereo (MVS) has long been a subject for researchers in the computer vision field. Due to the unreliable photometric consistency in low-textured areas, the existing PatchMatch MVS methods have low accuracy and completeness when recovering the depth information of low-textured areas in indoor environments. To solve the above problem that PatchMatch methods always fail in the textureless regions, we propose a global-local planar priors jointly optimized PatchMatch MVS method. The algorithm constructs global-local planar priors and uses a dynamic texture-related multi-view aggregation cost to balance photometric consistency and planar priors. The validity of the algorithm is verified by quantitative and qualitative analysis of depth maps and 3D reconstruction on multiple real-world scenes from ScanNet Dataset and ETH3D benchmark, also synthetic indoor scenes from ICL-NUIM Dataset. Our method can effectively recover the depth information in the textureless regions, so as to obtain the 3D model with high precision. [ABSTRACT FROM AUTHOR]

Image segmentation is a key problem in the field of machine vision. Its core goal is to separate the target and background in the region of interest from the image and directly affect the accuracy of subsequent operations such as target recognition and image understanding. In the past decades, there have been many good image segmentation algorithms. In recent years, the deep learning method represented by deep learning has made great progress in the field of image segmentation. In this paper, some commonly used image segmentation algorithms based on machine learning were reviewed, and their theoretical and experimental studies were carried out. In this paper, the application prospect of machine learning in image segmentation was prospected. The existing image segmentation methods are mainly divided into the following categories: threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and segmentation methods based on specific theories. In recent years, with the rapid progress of computer vision technology, the requirements for the accuracy of object image edge information segmentation have become increasingly high. The main reason for image segmentation is to better obtain object information. However, due to interference conditions such as lighting and noise, image blurry edge information segmentation has become the most difficult point in the development of computer vision technology. In the comparative experiment of algorithms, the results showed that in the training set, the response time of Deep Neural Network (DNN) algorithm, Cluster Analysis (CA) algorithm, and Support Vector Machine (SVM) algorithm was 13.72 s, 16.88 s and 17.29 s when the number of samples was 150. In the test set, when the sample number was 50, the recognition rate of DNN algorithm was 93.7%; the recognition rate of CA algorithm was 87.9%; the recognition rate of SVM algorithm was 84.3%. Therefore, the research of image fuzzy edge information segmentation based on computer vision and machine learning is essential. [ABSTRACT FROM AUTHOR]

The world's high-value crop is tea, its aspect plays a powerful role in its marketability. Tea is the utmost extensively absorbed aromatic beverage with the legion of health benefit and respond as a remedy for various disease like neurological disorder and cardiovascular. The identification of tea fermentation is onerous due to the heavy production of products. The manual investigation is expensive, laborious, and inconsistent. Thus, an automated machine learning-based algorithm is proposed for the grading of tea fermentation (fermented, over-fermented, under-fermented). Firstly, images are pre-processed by Gaussian filtering to enhance the quality of the image and removing of noise. Then various features namely, statistical, textural, color, geometrical, laws texture energy, the histogram of gradients, and discrete wavelet transform are extracted (150) and selected from feature vector by PCA. Lastly, k-NN, SRC, and SVM are used to make decisions for the detection of tea fermentation levels. The performance of the system has been validated by the k (10) fold cross-validation technique. The proposed algorithm achieves 87.39% (k-NN), 89.72% (SRC), and 98.75% (SVM) for tea fermentation level detection. The proper feature selection shows the enhanced performance of the system. Among three different classifiers, SVM shows more efficient results that are promising and comparable with the literature. This paper also includes the analytical comparison of distinct approaches proposed by the different researchers for tea fermentation level detection. This potential fermentation level detection may guide the detection of tea products which further promotes the development of the food industry. [ABSTRACT FROM AUTHOR]

In the present work, computer vision technology was adopted to study the effect of direct solar drying on quality attributes of turmeric in terms of color, morphology, texture, browning factor and shrinkage. Drying experiments were carried out with turmeric slices placed in an in-house built natural convection direct solar dryer. A standardized image acquisition unit was fabricated comprising LED strips and a digital camera for capturing the images of turmeric slices during the drying period. The color and shrinkage of sample were analyzed using RGB images in ImageJ software. The thickness of dried layer on the circumference of the sample was visualized using gray scale images in order to estimate the degree of polishing required for obtaining better quality samples. Browning determinant (BD) was computed using gray scale values of captured images and results showed decrement in BD with drying time revealing higher total phenolic content in dried turmeric in comparison to fresh sample. Lightness index (L*) was increased by 5.55%, while redness index (a*) and yellowness index (b*) were decreased by 117.06% and 278.26%, respectively during the entire drying period of 4 h. The morphological features like area, perimeter, roundness, solidity and density were found to decline smoothly with drying time by 83.72, 60.69, 22.34, 6.12, and 83.72% respectively. Fractal analysis was performed using scanning electron microscopy images and the micrographs showed rougher and more complex shaped particles for hot air dried turmeric (fractal dimension, DB = 1.78) powder as compared to solar dried powder (DB = 1.46). [ABSTRACT FROM AUTHOR]

This paper presents a system for automated, non-contact, and flexible prediction of surface roughness of end-milled parts through a machine vision system which is integrated with an artificial neural network (ANN). The images of milled surface grabbed by the machine vision system could be extracted using the algorithm developed in this work, in the spatial frequency domain using a two-dimensional Fourier transform to get the features of image texture (major peak frequency F, principal component magnitude squared value F, and the average gray level G). Since F1 is the distance between the major peak and the origin, it is a robust measure to overcome the effect of lighting of the environment. The periodically occurring features such as feed marks and tool marks present in the gray-level image can be easily observed from the principal component magnitude squared value F The experimental machining variables speed S, feedrate F, depth of cut D, and the response extracted image variables F, F, and G could be used as input data, and the response surface roughness R measured by Surfcorder SE-1100 (traditional stylus method) could be used as output data of an ANN ability to construct the relationships between input and output variables. The ANN was trained using the back-propagation algorithm developed in this work due to its superior strength in pattern recognition and reasonable speed. Using the trained ANN, the experimental result had shown that the surface roughness of milled parts predicted by machine vision system over a wide range of machining conditions could be got with a reasonable accuracy compared with those measured by traditional stylus method. Compared with the stylus method, the constructed machine vision system is a useful method for prediction of the surface roughness faster, with a lower price, and lower environment noise in manufacturing process. Experimental results have shown that the proposed machine vision system can be implemented for automated prediction of surface roughness with accuracy of 97.53%. The results are encouraging that machine vision system can be extended to many real-time industrial prediction applications. [ABSTRACT FROM AUTHOR]

Image texture provides a rich visual description of the surfaces in the scene. Many texture signatures based on various statistical descriptions and various local measurements have been developed. Existing signatures, in general, are not invariant to 3D geometric transformations, which is a serious limitation for many applications. In this paper we introduce a new texture signature, called the multifractal spectrum (MFS). The MFS is invariant under the bi-Lipschitz map, which includes view-point changes and non-rigid deformations of the texture surface, as well as local affine illumination changes. It provides an efficient framework combining global spatial invariance and local robust measurements. Intuitively, the MFS could be viewed as a “better histogram” with greater robustness to various environmental changes and the advantage of capturing some geometrical distribution information encoded in the texture. Experiments demonstrate that the MFS codes the essential structure of textures with very low dimension, and thus represents an useful tool for texture classification. [ABSTRACT FROM AUTHOR]

Tool wear monitoring is an integral part of modern CNC machine control. Cutting tools must be periodically checked for possible or actual premature failures, and it is necessary to record the cutting history for a tool’s full life of utilisation. This means that an on-line monitoring system would be of great benefit to overall process control in manufacturing systems. Computer vision has already shown promise as a candidate technology for this task. In this paper, we describe the use of digital image processing techniques in the analysis of images of worn cutting tools in order to assess their degree of wear and thus remaining useful life. It is shown that a processing strategy using a variety of image texture measures allows for effective visualisation and assessment of tool wear, and indicates good correlation with the expected wear characteristics. [ABSTRACT FROM AUTHOR]

In recent years, facial micro-expression recognition based on deep learning technology has become an important research hotspot. These techniques have been used by researchers in psychology, computer vision, and security to make breakthroughs. However, the proposed algorithm for micro-expression recognition faces some challenges in practical application. For example, the VGGMag method uses only one feature for micro-expression recognition, while the network cannot extract more useful features. The STRCN method does not focus on the key parts of facial micro-expressions, so that all parts of the face contribute equally to the micro-expression recognition model. A micro-expression recognition algorithm based on feature enhancement and attention mechanisms (FEAM) is proposed to further improve the recognition rate of micro-expressions. Firstly, the FEAM method designs a feature extraction module to extract micro-expression features and LBP image features, which preserves the texture information of the face. Secondly, the network constructs a feature augmentation module to highlight facial landmark points of faces as a way to increase the surrounding pixel weights. And then, the model designs the attention module to generate the attention correlation matrix of LBP and enhanced feature maps using the attention mechanism, which allows the network to pay more attention to the changes of features around the eyes and mouth of the face. Finally, the feature maps are input to the classification module for recognition. FEAM method is evaluated on three micro-expression datasets, and advanced results are obtained. The experimental results show that the proposed model FEAM can achieve state-of-the-art results compared to other models. [ABSTRACT FROM AUTHOR]

Computer vision for the past two decades has been used to simulate human capabilities and automate tasks, and in the process, has benefited all of us. Specifically, its application within the manufacturing context has garnered ample attention and interest from both academics and practitioners. Due to its large-scale applicability and adoption potential, extensive research has been conducted to understand and appreciate it is working. However, extant research in this domain is rather disjointed, thereby delimiting the otherwise vast scope and knowledge boundaries. Thus, this study utilizes bibliometric analysis to synthesize extant literature within this field to address this lacuna. We analyzed 897 articles from Scopus, entailing contributions from 309 journals, 108 countries, 2138 authors, and 1334 organizations from 1981 to 2022. Additionally, we analyzed citation and co-authorship networks to acknowledge prominent authors, organizations, and countries within this domain. The thematic classification of extant literature through bibliographic coupling identified five major thematic areas: automated visual inspection, object tracking and process controlling, real-time monitoring, roughness inspection, and profile projection. Importantly, we used both knowledge and insights from our findings, and propose scope for future research. [ABSTRACT FROM AUTHOR]

Damage to reinforced concrete (RC) facilities occurs through the process of natural deterioration. Machine learning can be employed to effectively identify various damage areas and ensure safety. The performance of machine vision methods depends on image quality. In this study, five image types (Types I–V) with combinations of image deficiencies pertaining to uniform illuminance, uneven illuminance, orthoimage, tilt angle, and image blur were used to evaluate the damage recognition capabilities of maximum likelihood (MLH), support vector machine (SVM), and random forest (RF) methods. Type I images were orthoimages with uniform illuminance, Type II images were tilted images with uniform illuminance, Type III images were orthoimages with uneven illuminance, Type IV images were tilted images with uneven illuminance, and Type V images were tilted, blurred images with uneven illuminance. MLH was most accurate (98.6%) in Type I images, and RF was the least accurate (62.8%) in Type V images. Image tilt (in Type II images) did not diminish the damage recognition capabilities of the three types of machine learning methods (mean accuracy = 97.2%). For tilted images with uneven illuminance (Type IV), a severe expansion effect was produced, reducing the mean accuracy to 70.1%. Type III images were recognized with a mean accuracy of 87.1%; uneven illuminance increased the error rate for three classes of damage. By testing various image types, the impact of image quality on the variability of machine learning recognition is understood, and the ability of automated machine learning recognition in the future is improved. [ABSTRACT FROM AUTHOR]

In the world, several sign languages (SL) are used, and BSL (Baby Sign Language) is the process of communication between the parents and baby using gestures. Communication by gestures is a non-verbal process that utilizes motion to pass on realities, expressions and feelings to people. SL is the communication mode in which the information is conveyed via movement of body parts like cheeks, eyebrows and head. Even though many research works based on SL are available, research in BSL remains a challenge. Hence, this paper presents an optimization-based automated recognition of the deep BSL system, which determines the gesture signalled by the kids. Initially, the image frames are extracted from the videos and data augmentation processes are performed. After pre-processing, the features are extracted from the frames using the Enhanced Convolution Neural Network (ECNN). The optimal characteristics are then selected by a new Life Choice Based Optimizer (LCBO). Finally, the classification is carried out by the Deep Long Short-Term Memory (DLSTM) scheme. The implementation is performed on the Python platform, and the performances are evaluated using several performance metrics such as accuracy, precision, kappa, f1-score and recall. The performance of the proposed approach (ECNN-DLSTM) is compared with several deep and machine learning approaches and obtains an accuracy of 99% and a kappa of 96%. [ABSTRACT FROM AUTHOR]

Pose-invariant facial expression recognition is one of the popular research directions within the field of computer vision, but pose variant usually change the facial appearance significantly, making the recognition results unstable from different perspectives. In this paper, a novel deep learning method, namely, soft thresholding squeeze-and-excitation (ST-SE) block, was proposed to extract salient features of different channels for pose-invariant FER. For the purpose of adapting to different pose-invariant facial images better, global average pooling (GAP) operation was adopted to compute the average value of each channel of the feature map. To enhance the representational power of the network, Squeeze-and-Excitation (SE) block was embedded into the nonlinear transformation layer to filter out the redundant feature information. To further shrink the significant features, the absolute values of GAP and SE were multiplied to calculate the threshold suitable for the current view. And the developed ST-SE block was inserted into ResNet50 for the evaluation of recognition performance. In this study, extensive experiments on four pose-invariant datasets were carried out, i.e., BU-3DFE, Multi-PIE, Pose-RAF-DB and Pose-AffectNet, and the influences of different environments, poses and intensities on expression recognition were specifically analyzed. The experimental results demonstrate the feasibility and effectiveness of our method. [ABSTRACT FROM AUTHOR]

Rapid growth in technology has changed the way humans live. Ongoing development in the automobile industry is creating intelligent vehicles and this mode of transportation will assist human society. The need for this survey arises to identify the scope of an intelligent vehicle through a computer vision approach equipped with recent technological trends. In this article, the major technological phases of intelligent vehicles are analyzed and discussed. The operational mechanism in these phases is mostly based on vision sensors that facilitate these vehicles to perceive the heterogeneous and dynamic environments and help them to make appropriate decisions. This study identifies various state-of-art techniques and phase-wise datasets used in the literature. It highlights the advancement in different phases, challenges, and scopes for the design and development of intelligent vehicles system. [ABSTRACT FROM AUTHOR]

Image decomposition into its structure and texture components is widely used in various image processing and computer vision applications. It is challenging to extract the structure component from an image having intricate texture since it is difficult to extract the structure from the texture that shares similar color intensity or scale. The aim of this work is to smooth the texture component from the image without affecting the significant image structures and to serve the purpose a structure- aware adaptive joint bilateral texture filtering has been employed. Main contribution in this paper is the designing of the guidance image, used in joint bilateral filtering for texture smoothing. To obtain high efficiency by using the proposed method, authors designed a scale map, which provides the size of the spatial kernel at each pixel using the characteristics of the structure and texture components. The experimental section demonstrates the supremacy of the proposed method over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

One of the essential elements of automated and intelligent machining processes is accurately predicting tool life. It also helps in achieving the goal of producing quality products with reduced production costs. This work proposes a computer vision-based tool wear monitoring and tool life prediction system using machine learning methods. Gradient-boosted trees and support vector machine (SVM) techniques are used to predict tool life. The experimental investigation on the CNC machine is conducted to study the applicability of the proposed tool wear monitoring system. Experiments are performed using workpiece material made of alloy steel and PVD-coated cutting inserts, and flank wear is monitored. An imaging system consisting of an industrial camera, lens, and LED ring light is mounted on the machine to capture tool wear zone images. Images are then processed by algorithms developed in MATLAB®. Boosted tree methods and the SVM methodology have 96% and 97% prediction accuracy, respectively. Validation tests are carried out to determine the accuracy of proposed models. It is observed that the prediction accuracy of boosted three and SVM is good, with a maximum error of 5.89% and 7.56%, respectively. The outcome of the study established that the developed system can monitor the tool wear with good accuracy and can be adopted in industries to optimize the utilization of tool inserts. [ABSTRACT FROM AUTHOR]

Large structures, such as bridges, highways, etc., need to be inspected to evaluate their actual physical and functional condition, to predict future conditions, and to help decision makers allocating maintenance and rehabilitation resources. The assessment of civil infrastructure condition is carried out through information obtained by inspection and/or monitoring operations. Traditional techniques in structural health monitoring (SHM) involve visual inspection related to inspection standards that can be time-consuming data collection, expensive, labor intensive, and dangerous. To address these limitations, machine vision-based inspection procedures have increasingly been investigated within the research community. In this context, this paper proposes and compares four different computer vision procedures to identify damage by image processing: Otsu method thresholding, Markov random fields segmentation, RGB color detection technique, and K-means clustering algorithm. The first method is based on segmentation by thresholding that returns a binary image from a grayscale image. The Markov random fields technique uses a probabilistic approach to assign labels to model the spatial dependencies in image pixels. The RGB technique uses color detection to evaluate the defect extensions. Finally, K-means algorithm is based on Euclidean distance for clustering of the images. The benefits and limitations of each technique are discussed, and the challenges of using the techniques are highlighted. To show the effectiveness of the described techniques in damage detection of civil infrastructures, a case study is presented. Results show that various types of corrosion and cracks can be detected by image processing techniques making the proposed techniques a suitable tool for the prediction of the damage evolution in civil infrastructures. [ABSTRACT FROM AUTHOR]

Image classification becomes a popular research area in computer vision due to the increasing development of image indexing and retrieval tasks. This paper proposes a Flower Henry Gas Solubility Optimization-based Deep Convolution Neural Network (FHGSO-based Deep CNN) for image classification. Initially, the input image is pre-processed through the median filter. Then, the segmentation is performed using the Improved Invasive Weed Flower Pollination Optimization (IIWFPO)-based SegNet. IIWFPO is the integration of the Improved invasive weed optimization (IWO) algorithm and Flower Pollination Algorithm (FPA). Finally, image classification is performed using FHGSO-based Deep CNN. The FHGSO algorithm is developed by integrating the FPA and Henry Gas Solubility Optimization (HGSO) algorithm. The performance of the proposed method is analyzed using the Stanford background dataset and compared with the other image classification methods. The proposed model obtained the value of 0.938, 0.955, and 0.907 for testing accuracy, sensitivity, and specificity, respectively. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNN) are being widely practised in computer vision applications, where pooling indicates as an integral part. Pooling significantly reduces the training time and computational cost of any network. The pooling operations generally being used are max, average, or stochastic. The performance of the CNN architecture can be increased by using more than one pooling operations. Herein, a novel mixed fuzzy pooling is proposed for image classification in the CNN architecture. In the proposed mixed fuzzy pooling, max pooling and fuzzy pooling are combined together to boost the classification accuracy. The proposed mixed fuzzy pooling is designed as a function of max pooling, fuzzy pooling, and α parameter where the learning of the proposed pooling function takes place with the value of α. In fuzzy pooling, Type-2 fuzzy logic is used to get the convolved dominant features. This is obtained by the estimation of a threshold for image region to be pooled. Thereafter, Type-1 fuzzy logic is used to get the pooling output by a weighted average of convolved dominant features. The performance of various pooling strategies on MNIST dataset for handwritten digits classification and CIFAR-10 dataset for RGB images classification have been compared and analysed. The experimental results show better image classification accuracy for the proposed mixed fuzzy pooling than conventional pooling operations. [ABSTRACT FROM AUTHOR]

Because the steel structure trestle has been in service under heavy load for a long time, the steel structure trestle is prone to cracks around the welds or bolt holes, which can lead to structural collapse in severe cases. Aiming at the characteristics of stable and high-quality images obtained by the unmanned consumer-grade camera monitoring system, this paper proposed structure health monitoring (SHM) system which is based on consumer-grade camera. The SHM system can identify crack damage and locate steadily in long term, which provides the technical support of practical application in intelligent SHM system. The method first performed edge detection on the trestle structure, followed by pixel-level semantic segmentation and crack localization. Canny edge detection algorithm was used to identify trestle structures in the camera image. The panorama trestle structure was divided into areas of suitable size, and the camera focused on each divided area one by one. Then the improved DeepLab V3+ model was trained by constructing global and local datasets. Then the improved DeepLab V3+ model was used to perform pixel-level semantic segmentation on the trestle images of the divided regions. Finally, based on the Speeded Up Robust Features and combined with the image, a panorama crack location output method was proposed. The system was used to test a section of a trestle in a coal mining industrial park, and the system showed that the method could efficiently and accurately identify and locate the crack damage. [ABSTRACT FROM AUTHOR]

Automating the fabric inspection process has been attempted by several researchers in the past. However, the numerous variants of fabric, such as their construction, texture, print, and colour along with the huge gamut of fabric defects which exist, complicate the process of automating defect detection, thus making it an open challenge for researchers to come up with a one-stop, full proof robust automation solution. In the present study, an attempt has been made to detect, classify, and locate four different types of fabric defects on solid wovens, hole, knot, slub and stain, which contributes 86% of total fabric defects; using the convolutional neural network (CNN) through transfer learning on the MATLAB® platform and computer vision technology. The image dataset in this study consists of 5000 images, which is one of the largest reported till date and collected from real working environments of different apparel manufacturing units. The methodology involves four different approaches—detection approach, hierarchical approach, classification approach, and object location approach. For algorithm development, transfer learning has been adopted in which the pre-trained deep learning architectures are fine-tuned as per specific case requirement. In this study, 4 state-of-the-art deep learning models were selected as follows: VGG16, VGG19, ResNet101 and DarkNet53. This study not only focuses on defect detection and classification but also on defect location which is detailed in its fourth approach. For object location, YOLOv3 architecture was used. The defect detection, classification and location identification systems attained an accuracy of 95%, 88% and 97%, respectively. The developed model was tested on different platforms viz. Internet-based webcam and MATLAB® cloud. Detailed investigation towards challenges faced by models specific to class of defect was carried out and reported thus adding insights for probable modification required in the model. The study proposes an industry ready system for real-time implementation. [ABSTRACT FROM AUTHOR]

Albeit Deep neural networks (DNNs) are widely used in computer vision, natural language processing and speech recognition, they have been discovered to be fragile to adversarial attacks. Specifically, in computer vision, an attacker can easily deceive DNNs by contaminating an input image with perturbations imperceptible to humans. As one of the important vision tasks, face verification is also subject to adversarial attack. Thus, in this paper, we focus on defending against the adversarial attack for face verification to mitigate the potential risk. We learn a network via an implementation of stacked residual blocks, namely adversarial perturbations alleviation network (ApaNet), to alleviate latent adversarial perturbations hidden in the input facial image. During the supervised learning of ApaNet, only the Labeled Faces in the Wild (LFW) is used as the training set, and the legitimate examples and corresponding adversarial examples produced by projected gradient descent algorithm compose supervision and inputs respectively. By leveraging the middle and high layer's activation of FaceNet, the discrepancy between an image output by ApaNet and the supervision is calculated as the loss function to optimize ApaNet. Empirical experiment results on the LFW, YouTube Faces DB and CASIA-FaceV5 confirm the effectiveness of the proposed defender against some representative white-box and black-box adversarial attacks. Also, experimental results show the superiority performance of the ApaNet as comparing with several currently available techniques. [ABSTRACT FROM AUTHOR]

Image segmentation refers to analysis of the images to understand its content, and now it is a very promising field of image processing and computer vision. The key objective of this study is to acquire optimal boundary lines to obtain the segmented images from heterogeneous datasets by tuning few relevant parameters of whale optimization algorithm (WOA) with long short-term memory (LSTM) network for heterogeneous datasets. In this paper, the LSTM has been explored to overcome the vanishing gradient problem of recurrent neural network (RNN) and the usefulness of stacked form of LSTM has been used to explore the depth of LSTM network which are more important than the number of memory cells given in a layer to model the skill. This study has been experimented with two LSTMs in a stacked form which provides a sequence output rather than a single value output to the LSTM layer below. Specifically, one output per input time step, rather than one output time step for all input time steps, is used to obtain the optimal and finer boundaries. The proposed tuned WOA hybridized with stacked form of LSTM for digital image segmentation strategy has been coined as S-LSTM-TWOA. The performance of the proposed model has been compared with hybridized S-LSTM network with genetic algorithm, particle swarm optimization, WOA and binary WOA techniques. The execution performance with respect to convergence speed, accuracy, execution time, Dice coefficient, intersection over union (IoU) is also recorded. The overall performance shows the segmentation capability of the proposed S-SLTM-TWOA to be more promising than the compared model by achieving approximately 99%, 99% and 98% for satellite images, BCN 20,000 and RVC 2020 datasets. [ABSTRACT FROM AUTHOR]

Recently, the progress on image understanding and AIC (Automatic Image Captioning) has attracted lots of researchers to make use of AI (Artificial Intelligence) models to assist the blind people. AIC integrates the principle of both computer vision and NLP (Natural Language Processing) to generate automatic language descriptions in relation to the image observed. This work presents a new assistive technology based on deep learning which helps the blind people to distinguish the food items in online grocery shopping. The proposed AIC model involves the following steps such as Data Collection, Non-captioned image selection, Extraction of appearance, texture features and Generation of automatic image captions. Initially, the data is collected from two public sources and the selection of non-captioned images are done using the ARO (Adaptive Rain Optimization). Next, the appearance feature is extracted using SDM (Spatial Derivative and Multi-scale) approach and WPLBP (Weighted Patch Local Binary Pattern) is used in the extraction of texture features. Finally, the captions are automatically generated using ECANN (Extended Convolutional Atom Neural Network). ECANN model combines the CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) architectures to perform the caption reusable system to select the most accurate caption. The loss in the ECANN architecture is minimized using AAS (Adaptive Atom Search) Optimization algorithm. The implementation tool used is PYTHON and the dataset used for the analysis are Grocery datasets (Freiburg Groceries and Grocery Store Dataset). The proposed ECANN model acquired accuracy (99.46%) on Grocery Store Dataset and (99.32%) accuracy on Freiburg Groceries dataset. Thus, the performance of the proposed ECANN model is compared with other existing models to verify the supremacy of the proposed work over the other existing works. [ABSTRACT FROM AUTHOR]