Search

Image processing has played a relevant role in various industries, where the main challenge is to extract specific features from images. Specifically, texture characterizes the phenomenon of the occurrence of a pattern along the spatial distribution, taking into account the intensities of the pixels for which it has been applied in classification and segmentation tasks. Therefore, several feature extraction methods have been proposed in recent decades, but few of them rely on entropy, which is a measure of uncertainty. Moreover, entropy algorithms have been little explored in bidimensional data. Nevertheless, there is a growing interest in developing algorithms to solve current limits, since Shannon Entropy does not consider spatial information, and SampEn2D generates unreliable values in small sizes. We introduce a proposed algorithm, EspEn (Espinosa Entropy), to measure the irregularity present in two-dimensional data, where the calculation requires setting the parameters as follows: m (length of square window), r (tolerance threshold), and ρ (percentage of similarity). Three experiments were performed, the first two were on simulated images contaminated with different noise levels. The last experiment was with grayscale images from the Normalized Brodatz Texture database (NBT). First, we compared the performance of EspEn against the entropy of Shannon and SampEn2D. Second, we evaluated the dependence of EspEn on variations of the values of the parameters m, r, and ρ. Third, we evaluated the EspEn algorithm on NBT images. The results revealed that EspEn could discriminate images with different size and degrees of noise. Finally, EspEn provides an alternative algorithm to quantify the irregularity in 2D data, the recommended parameters for better performance are m = 3, r = 20, and ρ = 0.7.

Feature extraction is a key step in image processing for pattern recognition and machine learning processes. Its purpose lies in reducing the dimensionality of the input data through the computing of features which accurately describe the original information. In this article, a new feature extraction method based on Discrete Modal Decomposition (DMD) is introduced, to extend the group of space and frequency based features. These new features are called modal features. Initially aiming to decompose a signal into a modal basis built from a vibration mechanics problem, the DMD projection is applied to images in order to extract modal features with two approaches. The first one, called full scale DMD, consists in exploiting directly the decomposition resulting coordinates as features. The second one, called filtering DMD, consists in using the DMD modes as filters to obtain features through a local transformation process. Experiments are performed on image texture classification tasks including several widely used data bases, compared to several classic feature extraction methods. We show that the DMD approach achieves good classification performances, comparable to the state of the art techniques, with a lower extraction time., 12 pages, 5 figures. Accepted and to be published in Pattern Recognition Letters

Based on image processing, feature extraction was a key part of against too much when Gabor filter to extract the texture feature parameters, difficult to find the appropriate parameters of the problem, after the analysis of mechanism of Gabor filter and various parameters, considering the characteristics of the intelligent algorithm is good at finding the optimal solution, designed by genetic algorithm selection, crossover and mutation operation, find out the objective function of the fitness of Gabor parameters, so as to realize the structure of the Gabor filter through the simulation, the scheme of the correctness of the Gabor filter.

Under long-term synergy effect of multi-factors, especially the thermal stress, insulating paper will be degraded and its insulation performance will decline due to carbonization and degradation of cellulose. This paper presents an optical approach for aging feature extraction of the insulating paper, where one of the image processing methods called texture analysis is utilized. By conducting laboratory accelerated thermal aging tests, insulating paper samples with different aging conditions for both Nomex and Kraft, evaluated with the aging time, are prepared. After taking optical microscopic images of insulating paper samples belong to different aging groups, up to 14 texture features are extracted using the gray-level co-occurrence matrix (GLCM). With different feature selection methods applied, several of them are finally selected to represent the aging condition of insulating. Numerical tests with both supervised and unsupervised algorithms, as well as a linear regression method verifies the validity of these features in characterizing the aging condition of the insulating paper.

One of the most important factors for deciding the use of wood product is knowing its strength class. So far, the wood strength has been measured using relatively expensive laboratory tests both for purchase and rent. In addition, this test has also damaged the test wood. An alternative method that can be used to determine the strength class of woods is to observe their characteristics using the naked eye. However, this is also a tough challenge because it must be done by wood experts who truly memorize and understand the characteristics of each wood class. Therefore, an image processing method is needed to identify the strength of wood easily, cheaply and not to damage test wood.The object of this study consisted of seven types of wood: Acacia (Acacia mangium), Teak (Tectona grandis), Mahogany (Swietenia mahagoni), Silk Tree (Paraserianthes falcataria), Sengon Tekik, Rain Tree (Samanea Saman) and Coastal Cottonwood (Hibiscus tiliaceus). Based on the results of specific gravity measurement, the wood strength classes of the test wood were as follows : Acacia, Teak and Mahogany were Class II, Rain Tree and Coastal Cottonwood were Class III, while Silk Tree and Sengon Tekik were Class IV.The parameters used by the author to determine the strength of wood based on image processing are the RGB color and texture of the wood image. We use two feature extraction methods, the average RGB histogram value for each color channel and the static characteristics of the Gray-Level Co-Occurrence Matrix (GLCM) method. The method used for feature selection is Recursive Feature Elimination Cross Validation (RFECV). While for data classification we use five algorithms: K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Decision Tree (CART), Random Forest (RF), and Support Vector Machine (SVM). The results of the qualifications showed that the highest accuracy was obtained by the KNN of 95%. Therefore, this method can be used as an alternative to determine the strength of wood.

Knee Osteoarthritis (OA) is one of the most prominent diseases in an ageing society and has affected over 10 million people in Thailand. When people suffer from OA, it is very difficult to recover. Therefore, early detection and prevention are important. The typical way to detect OA is by using X-ray imaging. This research study is focused on early detection of OA by applying image processing and classification techniques to knee X-ray imagery. The fundamental concept is to find a region of interest, use feature extraction techniques and build a classifier that can classify between OA or non-OA imageries. There are four regions of interest obtained from each image: (i) Medial Femur (MF), (ii) Lateral Femur (LF), (iii) Medial Tibia (MT), and (iv) Lateral Tibia (LT). The ten texture analysis techniques are then adopted to generate the embedded properties of the bone surface. Once the feature vector has been generated the variety of techniques of machine learning mechanisms are applied to generate the desired classifiers, which can be used to distinguish between OA and non-OA images. From the conducted experiments, a total of 131 images (68 OA cases and 63 non-OA cases) was used, the results obtained show that LF region with Local Binary Pattern descriptor produced the most appropriate classifier with an AUC value of 0.912.

The widespread penetration of counterfeit integrated circuits (ICs) is not only a major threat to the electronic goods supply chain, but also constitute a great threat to national security. Image processing based counterfeit IC design techniques are promising, but currently often suffer from high computational complexity and requirement of expensive image acquisition infrastructure. We describe two techniques based on image texture analysis to automate the process of counterfeit IC detection. The first method employs local textural feature identification to detect counterfeit ICs. The second method includes identification of counterfeit ICs by segmenting the image into regions of different textural features using texture filters. The first method is of lower computational complexity compared to the segmentation method, but the second method is capable of blind identification in the sense that it does not require knowledge of the textural features of a golden IC sample. Our experimental results show that these methods have high detection accuracy, even for images acquired using ordinary digital cameras and low-end digital microscopes.

This paper introduces an image texture analysis method for minority language identification. In the first stage, each letter is associated with a given script type according to its energy status in the text-line area. Mapping is carried out by extracting unicode text and transforming it into coded text. There are four different script types, which correspond to four grey levels of an image. Then, the obtained image is subjected to a feature extraction process performed by the texture analysis. This way, the grey level co-occurrence matrix and its derivative features are calculated. Extracted features are compared and classified using the K-Nearest Neighbors and Naive Bayes methods to establish a difference that can identify a minority language such as Serbian language among other world languages in the text. Very good accuracy results prove the efficiency of the proposed approach, when compared to other state-of-the-art methods.

Raveling is one of the critical and pervasive modes of failure observed in asphalt pavement road. Automatic detection of raveling based on image samples is a challenging task due to the complex texture of asphalt pavement. This study constructs and investigates the capability of an image processing based approach for raveling recognition. Image texture based features extracted from statistical properties of color channels and the Gray-Level Co-Occurrence Matrix are employed as input variables to characterize the state of pavement. The Stochastic Gradient Descent Logistic Regression (SGD-LR) is used to classify image samples into two categories of non-raveling and raveling based on a set of extracted features. A SGD-LR based raveling detection program has been developed in Visual C# .NET to facilitate its implementation. Experimental outcome shows that the newly constructed approach can attain a good predictive performance with a classification accuracy rate of roughly 88%. Therefore, this approach can be a helpful tool to assist transportation authorities in the task of surveying asphalt pavement condition.

We present an algorithm for risk prediction of road surface grip where skidding and sliding occur as main road surface problems. Prediction is done by defining a fine texture classification of the properties of road aggregate. In an experimental setup, data acquisition is performed with a supervised mobile vehicle scanning system, using a vehicle equipped with a camera and temperature sensor during movement along an arterial road. Image processing is performed by testing four texture feature extraction methods: Gabor filters, wavelet transform, gray level co-occurence matrix, and edge histogram descriptor, among which the Gabor transform shows the best results. The extraction of texture feature vectors follows by statistical algorithms for measuring feature vector similarity and reference vector selection, leading to image texture classification. The algorithm itself is upgraded by incorporating simultaneous surface temperature measurements in order to create and validate the final fine surface texture classification. The roads are classified and segmented into high-, medium-, and low-risk roads according to skid danger, enabling the creation of a map of high-risk zones. We validate our risk prediction algorithm by referring to crash rate data from the Road Traffic Safety Agency of Serbia database. This algorithm enables the location and mapping of high-risk zones and can be used as a support for autonomous driving and navigation.

In order to effectively extract Chinese herbal medicine (CHM) image feature information, and automatically identify the CHM images, a method of CHM image feature extraction and recognition based on gray level co-occurrence matrix (GLCM) is put forward. Firstly, on the basis of the acquired colour CHM image is converted to the gray-scale image, the four texture feature parameters, angular second moment (ASM)，inertia moment (IM)，entropy and correlation are extracted utilizing the GLCM, and then CHM image recognition is carried out by using those feature values with resistance geometric distortion. The experimental results show that the method of generating GLCM and extraction of image texture features can effectively identify the CHM image, which can bring significance to the modern recognition and identification of CHM.

To determine the real-time traffic state accurately in road network or intersections, traffic state identification method is proposed based on image processing technology. During the image process, by analyzing the image texture features, the multi-scale block local binary patterns are taken as the features. The road traffic state identification model is established based on support vector classification. A road section is taken as an example, the images of three traffic states (free traffic flow, steady traffic flow, and forced traffic flow) are selected to test the established traffic state identification model. This method can be applied to determine the real-time traffic conditions, which can provide information for the traffic management decisions.

Motivation: Physical properties of coal such as particle size distribution have a large influence on the stability and operational behavior of fluidized bed reactors and metallurgical furnaces. In particular, the presence of large amounts of ''fine'' particles invariably has a drastic effect on plant performance as a result of impaired gas permeability characteristics of the coal or ore burden. Therefore, monitoring and control of particle size distribution profiles of such aggregate material on reactor feed streams, such as moving conveyor belts, is critical for predictable operation of these processes. Traditionally, the method of sieve analysis using stock or belt cut samples has been widely used in industry. Unfortunately, the reliability and usefulness of belt cut techniques are constrained by frequency of sampling as well as laboratory analysis turnaround times. For real-time monitoring and control purposes, automated sampling and analysis methods are more desirable. Methods: In this study, the problem of estimating the particle size distribution profile of material on a moving conveyor belt is formulated within a texture classification framework, which has its basis in machine vision and incorporates elements from statistical pattern recognition. Using exemplar images of coal particles taken on a process stream, a set of local features that compactly describes the textural properties of each image are expressed in terms of localized nonlinear features called textons. Representation of image information using textons is primarily motivated by insights from neuroscience research on the optimality of linear oriented basis functions as models of perception in early processing of visual information in the cortex regions of the human brain. Using these representations for different textures, nearest neighbor and support vector machine classification models are subsequently used to classify test images. Results: Using a comprehensive evaluation, it is shown that the use of texton representation obtained from decomposing images with linear oriented basis functions can be sufficiently discriminative compared to the use of the widely used second-order statistical features or features from other baseline models. In particular, model performance obtained with appropriately tuned filters suggest the importance of including shape and spatial structure information in an image representation for texture classification of coal particles. Furthermore, using nonlinear support vector machines rather than nearest neighbor classifiers significantly improved classification performance. A texture classification approach to particle size profile estimation has potential applications in the online monitoring of the proportion of ''fines'' in coal material on moving conveyor belts.

Texture classification is very important in remote sensing images, X-ray photos, cell image interpretation and processing, and is also the active research areas of computer vision, image processing, image analysis, image retrieval, and so on. As to spatial domain image, texture analysis can use statistical methods to calculate the texture feature vector. In this paper, we use the gray level co-occurrence matrix and Gabor filter feature vector to calculate the feature vector. For the feature vector classification under normal circumstances we can use Bayesian method, KNN method, BP neural network. In this paper, we use a statistical classification method which is based on SVM method to classify images. Image classification generally includes image preprocessing, image feature extraction, image feature selection and image classification in four steps. In this paper, we use a gray-scale image, by calculating the image gray level cooccurrence matrix and Gabor filtering method to get feature extraction, and then use SVM to training and classification. From the test results, it shows that the SVM method is the better way to solve the problem of texture features for image classification and it shows strong adaptability and robustness for image classification.

Texture classification is an important and challenging factor in image processing system which refers to the process of partitioning a digital image into multiple constituent segments. The goal of segmentation is to simplify and / or change the representation of an image into something that is more meaningful and easier to analyze. Artificial Neural Network (ANN) Based texture classification or Segmentation is an advanced technique providing rich information of an image of interest. As a part the work, an ANN is implemented to segment the image. For that a particular type of ANN is configured and trained so that it becomes capable of segmenting an image. The current work deals with a task where an object of interest is to be segmented out of a background for processes which can be carried out as part of extended applications.

Over the past several years we have been interested in the supervised classification of ultrasonic images of the liver based on quantitative texture features. Our most recent efforts are concerned with the inclusion of features computed from Markov random fields. After adding four such features to our existing model containing 17 features, we employed stepwise discriminant analysis to identify the features that could best discriminate among 184 previously classified normal and abnormal ultrasonic images. Three of the four features derived from Markov random field models were identified by stepwise discriminant analysis as being good discrimination along with 6 existing features. From these results we constructed a backpropagation neural network with an input layer consisting of 9 nodes. We found that this new model yielded slightly better results when compared to earlier models. Our most recent results yielded a sensitivity of 81%, a specificity of 77% and an overall accuracy of 79%.

With the increasing amount of digital image data, massive image process and feature extraction process have become a time-consuming process. As an excellent mass data processing and storage capacity of the open source cloud platform, Hadoop provides a parallel computing model MapReduce, HDFS distributed file system module. Firstly, we introduced Hadoop platform programming framework and Tamura texture features. And then, the image processing and feature texture feature extraction calculations involved in the process to achieve Hadoop platform. The results which comparison with Matlab platform shows it is less obvious advantage of Hadoop platform in image processing and feature extraction of lower-resolution images, but for image processing and feature extraction of high-resolution images, the time spent in Hadoop platform is greatly reducing, data processing capability the advantages is obvious.

A new technique for image texture analysis is described which uses the relative frequency of local extremes in grey level as the principal measure. This method is invariant to multiplicative gain changes (such as caused by changes in illumination level or film processing) and is invariant to image resolution and sampling rate if the image is not undersampled. The algorithm described is computationally simple and can be implemented in hardware for real-time analysis. Comparisons are made between this new method and the spatial dependence method of texture analysis using 49 samples of each of eight textures. The new method seems just as accurate and considerably faster.

Previous approaches to texture analysis and segmentation use multichannel filtering by applying a set of filters in the frequency domain or a set of masks in the spatial domain. This paper presents two new texture segmentation algorithms based on multichannel filtering in conjunction with neural networks for feature extraction and segmentation. The features extracted by Gabor filters have been applied for image segmentation and analysis. Suitable choices of filter parameters and filter bank coverage in the frequency domain to optimize the filters are discussed. Here we introduce two methods to optimize Gabor filter bank. First, a Gabor filter bank with a flat response is implemented and the optimal feature dimension is extracted by competitive networks. Second, a subset of Gabor filter bank is selected to compose the best discriminative filters, so that each filter in this small set can discriminate a pair of textures in a given image. In both approaches, multilayer perceptrons are employed to segment the extracted features. The comparisons of segmentation results generated using the proposed methods and previous research using Gabor, discrete cosine transform (DCT), and Laws filters are presented. Finally, the segmentation results generated by applying the optimized filter banks to textured images are presented and discussed.

To effectively detect the surface cracks of subway tunnels, an automatic tunnel crack detection system based on machine vision is presented. Aiming at the problems of environmental complexity and low contrast in subway tunnels, the image texture feature is first enhanced by the methods of frequency domain filtering and spatial differencing. Then, depending on the characteristics of the tunnel cracks in question, the crack propagation method is used to extract the complete cracks. Finally, broken cracks are connected during processing, and the method of combining projection and threshold is used to determine the crack types. At the same time, characteristics such as the length, width, and area of the cracks are obtained. The experimental results show that the presented methods can effectively extract complete cracks in complex tunnel environments. The identification error of tunnel crack parameters meets the actual engineering requirements.

Image regularised features play a critical role in image processing domain, by integrating regularised feature and structural similarity, a new full-reference image assessment method (IRF_SSIM) is proposed in this study. As well known, the gradient operator always be used to capture the edge information of the image, while the total variational regularised features can be adopted to calculate the detailed change information of image contrast and texture, as well as noise removal and edge retention. Therefore, the IRF_SSIM method extends the gradient features into the image regularised features to measure the structural changes in the image. In addition, image quality is also affected by variations of luminance and contrast. For a more comprehensive image quality assessment, the IRF_SSIM method considers the changes in structure, luminance and contrast simultaneously. In other words, the total image quality is estimated by structural similarity calculated by integrating the effects of image structure, luminance and contrast changes. Comparing with the representative methods, the experimental results illustrate that the IRF_SSIM method is highly consistent with the subjective assessment results.

Image segmentation is one of the most important aspects of image processing that has many applications in image analysis, computer vision, and machine vision. So far, researchers have proposed many image segmentation algorithms that provide a relatively appropriate response for a particular application and over a specific type of input images. At the same time, they have not yet suggested a simple, fast, and efficient segmentation method that can apply to a wide range of natural and texture images. In this study, the authors present a new adaptive method for selecting Gabor filters using the image frequency content. Adaptive spectral features of the image are then extracted using only these selected filters from a Gabor filter bank. A pre-setting parameter Gabor filter is used to extract the gradient of each feature in x and y directions. Combining these features gradient, the texture gradient image is calculated, and then by selected markers for different texture regions and applying the marker-based watershed transform on texture gradient image, the authors present a new image segmentation method that has a less computational cost and yields better results compared to using all other filter banks.

Transferring a photo to a stylised image with beautiful texture has become one of the most popular topics in computer vision and the application of image processing. Controlling the stroke size of the texture is one of the challenging problems in this task. Recent representative methods for such problem introduce a pyramid model to regulate receptive fields in the network. Meanwhile, dilated convolutions are proved to be a very efficient way to adjust receptive fields without losing resolution. By combining the advantages of both approaches and making special optimisation for VGG19 model for style transfer tasks, the authors propose to exploit dilated convolutions to extract texture information endowing the network with stroke controllable. Several sets of contrast experiments were conducted and results show that their algorithm can generate more attractive stylisation images and control stroke size flexibly. It demonstrates the superiority of applying dilated convolutions as a texture extraction method for maintaining more texture information and controlling stroke size.

Part of important structural edges in the image is smoothed due to the small gradients, while the others are preserved with greater gradients. Therefore, the authors propose a two-stage image smoothing method based on edge-patch histogram equalisation and patch decomposition. The authors' purpose is to increase the gradient of important structural edges while reducing the gradient of the texture region. Therefore, they divide the image into edge-patches where the structural edges are concentrated or non-edge-patches where the texture details are concentrated by image segmentation. The edge-patch needs to be equalised by the histograms for increasing the gradient of the edge pixels. All patches are decomposed to extract the smooth component for reducing the gradient of pixels. The smooth component of each patch is smoothed via L 0 gradient minimisation. In order to ensure the continuity of the patch boundaries, the edge-patch is inversely equalised. Finally, the whole image is smoothed via L 0 gradient minimisation for removing residual textures and seams. Experimental results demonstrate that the proposed method is more competitive in maintaining important structural edges and removing texture details than the state-of-the-art approaches. The proposed method can be applied to many areas of image processing.

Image processing is a computational process that transforms one or more input images into an output image. Image processing is frequently used to enhance an image for human viewing or interpretation, for example to improve contrast. Alternatively, and of more interest to robotics, it is the foundation for the process of feature extraction which will be discussed in much more detail in the next chapter.

Damage mechanisms of Reactive Powder Concrete (RPC) under fatigue loading are investigated using the 3D laser scanning technology. An independently configured 3D laser scanning system is used to monitor the damaging procedure. Texture analysis technique is also applied to enhance the understanding of the damage mechanisms of RPC under fatigue loading. In order to obtain the characteristic parameters of point cloud data, a point clouds projection algorithm is proposed. Damage evolution is described by the change of point cloud data of the damage in the 2D plane and 3D space during fatigue loading. The Gray Level Co-occurrence Matrix (GLCM) method is used to extract the characteristic parameters to evaluate the statue of the structural. Angular Second Moment and Cluster Shadow of typical sensitive characteristic indexes is screened by using the Digital Feature Screening. The reliability of the damage index was verified by image texture analysis and data expansion. Indexes extracted in this paper can be used as a new structural health monitoring indicator to assess health condition.

Structure–texture decomposition is one of the fundamental branches of computer vision and image processing. It is not only beneficial to image understanding but also to subsequent object recognition and tracking. However, diversity and complexity of textures impede structure extraction. In this study, a simple yet effective structure–texture decomposition method is proposed based on directional relative total variation. More concretely, the directionality of relative total variation is taken into account by using the directional gradient operator instead of partial derivatives both in x and y directions. In addition, in order to explore the directional information on different scales, the non-subsampled pyramid filter bank is employed to obtain the multi-scale properties. Experiments on a wide variety of images reveal the efficacy of the proposed method and show its superiority over several state-of-the-art methods. Besides, the applicability of the proposed method to several image processing tasks is also demonstrated, such as edge extraction, defect detection, and so on.

Pectoral muscle segmentation is a very important step in any Computer Aided Detection (CAD) system, for automatic detection of different possible signs of malignancy in the mammographic image. Presence of high-density glandular tissues overlapping pectoral muscle boundary, presence of pectoral muscle of small size and low density, presence of pectoralis minor etc., poses a great challenge for researchers working on the problem of automatic pectoral muscle boundary detection. Gabor filter has been used by many researchers to detect textural edges. The ability that it can be tuned along a particular direction, makes it a very important image processing tool. In the proposed research work a Gabor filter tuned in the direction of pectoral muscle boundary is applied on the region of interest (ROI) containing pectoral muscle. Finally, the magnitude and phase response of Gabor filtered ROI image along with an edge-connect and region merge algorithm is used to detect pectoral muscle boundary. The proposed method is validated using 200 mammograms from the miniMIAS database and 200 mammograms from INbreast database. With an accuracy of 97.50% for miniMIAS database and 94.50% for INbreast database, the proposed method outperforms many state-of-the-art methods which show its suitability for CAD Systems.

In civil engineering, crack detection using image processing has gained much attention among researchers and transportation agencies. As the crack image often presents a fuzzy boundary and random shape, it is difficult to achieve satisfactory detection performance. This study proposes a crack detection method based on the fractional differential and fractal dimension. This method achieves image enhancement and crack extraction in two stages. First, an image enhancement algorithm based on the fractional differential is applied to solve the fuzzy crack boundary. This algorithm can enhance the crack boundary information significantly while simultaneously maintaining texture details. Second, an improved extraction algorithm based on the fractal dimension is studied. This algorithm can effectively accomplish crack extraction according to shape features. Last, upon comparisons with classic and state-of-the-art methods, the experiment shows that the proposed method can achieve satisfactory results for crack image detection.

This study presents a novel feature extraction approach based on image processing algorithms for the automated detection of epileptic seizure activities in brain map representation of electroencephalography (EEG) signal using an efficient classification technique. The proposed technique uses independent component analysis to extract independent components (ICs) from the EEG signal and each extracted IC is transformed into an image termed as brain maps. Two feature extraction techniques namely closed neighbourhood gradient pattern (CNGP) and combined texture pattern (CTP) are propounded for automatic elimination of artefact brain maps. The extracted features are fed into the least square support vector machine (LSSVM) for automatic detection of epileptic brain maps. Extensive experimental result over the existing image processing techniques in literature demonstrates that the texture pattern representations of CNGP and CTP are improved to obtain better features to enhance the performance of texture classification. The obtained result shows that the LSSVM classifier with Gaussian RBF kernel is able to detect the epileptic brain map with a high accuracy rate. The results are reliable and it assists the neurologist to diagnose epileptic signals effortlessly by visually locating the brain area being affected by seizure activities.

In pixel classification-based segmentation both the quality of the feature set and the pixel classification technique employed may influence the accuracy of the process. Motivated by the potential of Structural Tensors in the extraction of hidden information about texture between neighboring pixels and the computational capabilities of Echo State Network (ESN), this study proposes a tensor-based segmentation approach using the standard ESN. The pixel features of the image are initially extracted by incorporating Structural Tensors in order to enrich it with information about image texture. Then the resulting feature set is fed into ESN and the output is trained to classify unseen pixels from the testing set. The effect of the two main parameters that impact the accuracy of ESN: reservoir size and spectral radius, was also evaluated. The results are promising when compared to recent state-of-the-art segmentation approaches.

Agriculture is the dominant sector of our economy and contributes in various ways but the yield in the productivity leads to a significant reduction in the farmer’s income. Monitoring crop health is important to increase the quality and quantity of the yield. But this requires manually monitoring the crops and also expertise in the field. Hence, automatic disease detection using image texture features is used for ease and to detect the disease at an early stage. The proposed methodology for the project is to design and implement the algorithm on two sets of databases: firstly, a locally generated leaf database which contains images of leaves and secondly, a standard database which is a common test database. The basic steps for crop disease detection include image acquisition, image preprocessing, image segmentation, feature extraction, and classification using image processing techniques. The acquired leaf images are preprocessed by removing undesired distortion and noise, and then, the processed image is further subjected to K-means-based segmentation. The segmented image is further analyzed using Haar wavelet transform and GLCM based on its texture by extracting feature vector. SVM is used for classification of image. Thus, the presence of diseases in leaf is identified along with all the features values of the leaf. It also calculates the accuracy rate of the prediction made by the system.

To achieve the rotor winding qualification test, a new detection method based on texture information and convolution neural network is proposed. This method could effectively eliminate the effect of illumination by using LBP to extract image texture information in advance which is calculated by circular radius, and then using convolution neural network to extract features in further to discriminate the workpiece is qualified or not, which can put the discrimination accuracy to a higher stage. The experimental results prove it, which shows that the new method in this paper performs better than traditional methods no matter of the accuracy rate or the time it costs.

In side scan sonar image processing, the target area and the shadow area are important features of the underwater target. Segmenting it from a background image is an important step in subsequent image recognition. However, the common segmentation algorithms have serious background interference, serious loss of edge contour information, and inconsistent target area and shadow area. Aiming at these shortcomings, this paper proposes an improved Markov random field (MRF) based texture image segmentation algorithm. The feature vector field is used instead of the original MRF observation field, where the feature vectors are obtained by the gray level co-occurrence matrix, the fractional differential operation and the Zipf’ s law. In this paper, we compare the results of using three algorithms together and three algorithms respectively on the real side scan sonar image. It turns out that using the three methods together, that is, using the integrated feature vector, a more ideal segmentation effect can be obtained.

With the rapid development of intelligent image processing and computer vision, interpreting and extracting emotion information from images have become a hot research topic, especially the studies on film and television scene images with rich expressions and certain feelings from the aspect of audience. To investigate the distribution of emotions and its affect on the result of machine learning, this paper established the emotion classification models with different salient and non-salient regions based on self-built dataset from film and television works. Three salient extraction algorithms were used to the regional segmentation, and the color and texture features of each region were extracted. Emotion classification models were established based on SVM and RF algorithms respectively. Since features of the salient region could not cover all the information of the original image, the prediction accuracy of the unprocessed image was the highest. Nevertheless, when models made an error in the emotion prediction of the original image, the experimental results of salient region could get the correct answer under the certain circumstances. Through the analysis, the areas of interest can be used for emotion prediction to reduce the redundancy; however, to make it more accurate, the appropriate salient region extraction algorithm should be selected for different types of images and features. Our study provides data and theoretical guidance for image understanding and retrieval, and it has practical significance for more detailed classification based on the affective sensation.

The segregation of asphalt pavement is the main reason for the decrease of safety, comfort and actual service life of the road, and the paving segregation is the main inducement for asphalt pavements segregation. Thus, a kind of effective paving segregation detection method can reduce the occurrence of asphalt pavement segregation. The traditional asphalt segregation detection methods are mainly divided into contact detection and non-contact detection. The contact detection method can only detect the segregation of pavement after paving or in use, and the non-contact detection method is also generally limited by the noise and expensive equipment. In recent years, the rapid development of image processing technology has provided a new research direction for asphalt paving segregation detection, but the accuracy and efficiency of the existing image-based asphalt paving segregation detection methods are insufficient. In order to solve these problems, this paper proposes an asphalt paving segregation detection method based on image texture features. Firstly, based on the traditional algorithms LBP (Local Binary Pattern) and GLCM (Gray-level Co-occurrence Matrix), a new texture feature extraction algorithm uniform pattern LBP-GLCM is proposed. Secondly, a detection method based on uniform pattern LBP-GLCM in combination with SVM (Support Vector Machine) is proposed. Then, the detection method proposed is validated using Kylbery texture dataset, the result show that this detection methods has great accuracy and efficiency in the classification of targets with similar texture features, it also means the texture feature extract method based on uniform pattern LBP-GLCM can combine the advantages of LBP and GLCM to achieve improvement of feature extraction's performance and efficiency. Finally, the detection method is applied to the diagnosis of asphalt paving segregation, and the accuracy of diagnosis achieves 94%. Compared with the existing algorithms, detection method based on uniform pattern LBP-GLCM has higher diagnostic accuracy and efficiency. Specifically, detection method with uniform pattern LBP-GLCM can improve accuracy in comparison with single asphalt pavement paving segregation detection method, and it can improve efficiency in comparison with existing hybrid asphalt pavement paving segregation detection method. The results of this study can potentially be used for real-time detection of asphalt paving segregation.

A novel multivariate textural feature extraction for epileptic EEG analysis.EEG channels are mapped into gray-scale to form a texture image.Low-cost and compact representation of multi-channel epileptic EEG records.We perform an extensive comparison against other state-of-arts dedicated methods.Epilepsy detection with high sensitivity rate and low number of false alarms. Interpretation of long-term Electroencephalography (EEG) records is a tiresome task for clinicians. This paper presents an efficient, low cost and novel approach for patient-specific classification of long-term epileptic EEG records. We aim to achieve this with the minimum supervision from the neurologist. To accomplish this objective, first a novel feature extraction method is proposed based on the mapping of EEG signals into two dimensional space, resulting into a texture image. The texture image is constructed by mapping and scaling EEG signals and their associated frequency sub-bands into the gray-level image domain. Image texture analysis using gray level co-occurrence matrix (GLCM) is then applied in order to extract multivariate features which are able to differentiate between seizure and seizure-free events. To evaluate the discriminative power of the proposed feature extraction method, a comparative study is performed, against other dedicated feature extraction methods. The comparative performance evaluations show that the proposed feature extraction method can outperform other state-of-art feature extraction methods with a low computational cost. With a training rate of 25%, the overall sensitivity of 70.19% and specificity of 97.74% are achieved in the classification of over 163h of EEG records using support vector machine (SVM) classifiers with linear kernels and trained by the stochastic gradient descent (SGD) algorithm.

In this paper, a new 2D-DOST (Two-Dimensional Discrete Orthonormal Stockwell Transform) and LS-SVM (Least Squares Support Vector Machines) based classifier system is proposed for classification of texture images. The proposed system contains two main stages. These stages are feature extraction and classification. In the feature extraction stage, the distinguishing feature vectors which represent descriptive features of texture images are obtained by using a 2D-DOST based feature extraction method. In the classification stage, the texture images are classified by the LS-SVM since this classifier has high success rate and accuracy. The training of LS-SVM is performed on the distinguishing feature vector of each texture component. Texture samples are recognized by the test data applied to the input of trained LS-SVM classifier. Performance evaluations of the proposed method are carried on different datasets obtained from sub-images. These datasets include both the normal texture images and noise added images. Sub-images into datasets are derived from Brodatz and Kylberg texture images database. Gaussian and Salt & Pepper noise with different levels are used for creating noisy datasets. According to the study results, the proposed 2D-DOST and LS-SVM based classifier has a capability of classifying texture images with high success rate and noise robustness.