Image texture classification is crucial in machine vision and image processing. The primary step in this classification process involves extracting features from the image. Numerous techniques have been developed for feature extraction from textured images; however, local binary patterns (LBP), in both their original and enhanced forms, stand out due to their simplicity in implementation and their ability to extract effective features that yield high classification accuracy. Experts widely recognize that deep neural networks excel at classifying images and extracting detailed features. Building on the strengths of these methods, this study introduces a new model that merges deep learning with enhanced local binary patterns. This model has been tested on the Outex and CUReT datasets. The experimental results indicate that combining deep learning with an improved local binary pattern method significantly enhances the accuracy of texture image classification. According to these results, the classification accuracy of this new model surpasses that of previous methods.

New applications such as 3D graphics, 3D displays, and image-based modeling have made stereo vision an active research area in recent years. In dense disparity map estimation, which is a basic problem in stereo vision, using two left and right images taken from a scene from two different positions, the disparity of each pixel of the reference image is determined (meaning determining each pixel with how displacement is appeared in the other image). Based on the disparity value, the depth of each pixel in scene is simply determined. For dense disparity map estimation, local stereo matching methods are simpler and faster than global methods, and therefore suitable for real time applications. In these methods, defining proper window which aggregate intensity pattern as well as keeping disparity consistency in all the window area, is an important challenge. To overcome this challenge, the idea of directional multiple window has been proposed in the previous researches. On the other hand, local binary patterns have considerable success in pattern recognition applications, while computationally simple. Therefore, the idea of using local binary pattern in a directional multiple window arrangement is proposed for dense stereo matching in this paper. Experimental results on standard stereo images show the better performance of the proposed method with respect to other proposed binary descriptors

Facesketchsynthesis of example image plays an important role in both digital entertainment and law enforcement. In this paper, face sketch synthesis has two main processes. In the first process, neighbors are selected and in the second process, reconstruction weight representation is done. Running time and computation complexity depends on neighbor patches selection process. Face sketchgeneration with state-of-the-art methods perform neighbor selection process in a data-driven manner by K nearest neighbor searching. Hence, the running time for synthesisincreases. Also, for neighbor selection need to check the whole training dataset. As a result, the computational complexity increases with the scale of the training database and is limited scalability. In this paper, we proposed a simple but effective with encoding local binary pattern and random sampling in place of pixels. Then by extracting shape from resulting textures and determining state of surfaces, we represent facial sketch. Our experiments onpair of CUHK database imagesdemonstrate the proposed method in comparison to state-of-the-art methods has superiorityof view generated sketch quality and running time. Also, the proposed methodin front of face hallucinationproblemswhich cause heterogeneous transformation on facial sketch is resistant.

Distinctive and efficient description of image features is an essential task for image registration in photogrammetry and remote sensing. The majority of existing descriptors estimate a dominant orientation parameter for rotation invariant image matching. The dominant orientation assignment is an error-prone process, and it decreases the capability of the descriptors. In this paper, a novel feature descriptor based on the local binary pattern operator named RILBP (Rotation Invariant Local Binary Pattern) is proposed that is inherently rotation invariant. To compute the RILBP descriptor, the pixels in the given image region are divided into several sub-regions based on distance and intensity order constraints. Then, a local binary pattern histogram is generated for each sub-region based on a rotation invariant coordinate system. To increase the descriptor robustness against geometric distortions, a special weighting process based on a combined ring and Gaussian functions is applied. The proposed RILBP descriptor was successfully applied for matching of various remote sensing images as: SPOT 5, ETM+, Sentinel 2, IKONOS, IRS P6 and ZY3 sensors, and the results demonstrate its capability compared to common feature descriptors such as CS-LBP, SIFT, LSS, and MROGH. Compared to the standard CS-LBP descriptor, the RILBP descriptor indicates an average performance improvement of about 25%, 10% and 30%, in terms of Recall, Precision and number of correct matches, respectively.

Stroke patients generally exhibit trouble walking and moving, which affects their quality of life. Hence, an accurate diagnosis of stroke is important for providing an effective treatment and rehabilitation strategy. However, the development of a cost-effective and non-invasive diagnostic tool is a big challenge for clinical applications. To address this challenge, in this study, a new ischemic stroke detection has been proposed based on structural features of foot plantar pressure signals and support vector machine classifier. A local uniform binary pattern extracted from the time-frequency representation of pressure signals has been used to capture the local structure over two-dimensional space and quantify the stability of this pattern. The proposed method has been evaluated using the pressure signals recorded during normal walking tasks from 36 healthy controls and 46 Ischemic stroke patients. The classification has also been performed for different plantar channels to offer regional analysis. The obtained results have achieved a high average accuracy rate of 99.66% for stroke detection. Furthermore, the robustness of the proposed method against different plantar regions as well as technical parameters of the local binary pattern approach has been demonstrated in an experimental comparative study. The performance has confirmed that the local binary pattern analysis discriminates effectively stroke patients and healthy controls when foot plantar pressure signals are used.

Texture classification is one of the important branches of image processing. The main point of texture classification is feature extraction. Local Binary Pattern (LBP) is one of the important methods that are used for texture feature extraction. This method is widely used because it has simple implementation and extracts high discriminative features from textures. Most of previous LBP methods used uniform patterns and only one feature is extracted from non-uniform patterns. In this paper, by extending non-uniform patterns a new mapping technique is proposed that extracts more discriminative features from non-uniform patterns. So in spite of almost all of the previous LBP methods, the proposed method extracts more discriminative features from non-uniform patterns and increases the classification accuracy of textures.The proposed method has all of the positive points of previous LBP variants. It is a rotation invariant and illumination invariant method and increase the classification accuracy. The implementation of proposed mapping on Outex dataset shows that proposed method can improve the accuracy of classifications significantly.

Background: Osteoporosis is a systemic skeletal disease characterized by low bone mineral density (BMD) and micro-architectural deterioration of bone tissue, leading to bone fragility and increased fracture risk. Since Panoramic image is a feasible and relatively routine imaging technique in dentistry; it could provide an opportunistic chance for screening osteoporosis. In this regard, numerous panoramic derived indices have been developed and suggested for osteoporosis screening. Jaw trabecular pattern is one of the main bone strength factors and trabecular bone pattern assessment is important factor in bone quality analysis. Texture analysis applied to trabecular bone images offers an ability to exploit the information present on conventional radiographs. Objective: The purpose of this study was to evaluate the relationship between Jaw trabecular pattern in panoramic image and osteoporosis based on image texture analyzing using local binary pattern. Material and Methods: An experiment is evaluated in this paper based on a real hand-captured database of panoramic radiograph images from osteoporosis and non-osteoporosis person in Namazi Hospital, Shiraz, Iran. An approach is proposed for osteoporosis diagnosis consisting of two steps. First, modified version of local binary patterns is used to extract discriminative features from jaw panoramic radiograph images. Then, classification is done using different classifiers. Results: Comparative results show that the proposed approach provides classification accuracy about 99. 6%, which is higher than many state-of-the-art methods. Conclusion: High classification accuracy, low computational complexity, multiresolution and rotation invariant are among advantages of our proposed approach.

Local binary pattern is one of the most popular descriptor that widely used in feature extraction of texture images. Deep convolutional neural network is also one of the best classification methodthat provides very high accuracy. In this research, by combining the features that produced by these two methods, a structure for noisy texture classification is proposed, which provides a very high classification rate. This method is based on two extracted features. The first part uses completed local binary pattern features and in the second part the features of texture images are extracted by using the DenseNet-121 convolution deep neural network. Another motivation of this research related to feature reduction, which significantly reduces the dimensions of extracted features. It employs a shallow convolution neural network to convert the extracted features into lower number of new features. The accuracy of the proposed method has been evaluated on noisy Outex, CUReT and UIUC datasets. The classification accuracy of the proposed method for different level of noise has increased significantly compared to many advanced methods and has improved between 3 and 25%.