Uniform Local Binary Pattern Research Articles

Deep recurrent neural networks distributed on a Hadoop/Spark cluster for fall detection

Falls detection approaches struggle with both Big Data scalability and upholding individual privacy, this research work proposed a novel approach for posture recognition followed by fall detection, taking advantage of the synergy between Random Forests and Uniform Local Binary Patterns (uLBP) histograms for an accurate and fast posture identification while respecting privacy. Additionally, it referred to deep recurrent neural networks distributed on a Hadoop and Spark platform for time series analysis in fall detection. This combination of methods allowed us to achieve acceptable real-time monitoring precision. This study, therefore addressed two objectives simultaneously: efficiency and scalability in posture recognition using Random Forests and uLBP, and fall detection relying on the recurrent neural network (RNN) for time series processing. The suggested solution is designed for home telemonitoring, where scalability and effective data management are supported through Hadoop/Spark. The integration of these technologies promotes reliable detection without any privacy violation, paving the way for a wider adoption of home monitoring systems for an increasing population of dependent individuals.

Decoding Student Emotions: An Advanced CNN Approach for Behavior Analysis Application Using Uniform Local Binary Pattern

Decoding Student Emotions: An Advanced CNN Approach for Behavior Analysis Application Using Uniform Local Binary Pattern

Data Augmentation for Genetic Programming-Driven Late Merging of HOG and Uniform LBP Features for Texture Classification

The categorization of texture images requires the identification and extraction of meaningful keypoints, a crucial step in ensuring the precise representation of textured images. The literature has introduced numerous descriptors in order to detect and capture both local and global texture characteristics. These descriptors vary in their effectiveness depending on the specific application. However, it is generally accepted that they complement each other by compensating for their strengths and weaknesses. Therefore, many approaches focused on combining different types of image descriptors generating robust features that are invariant to image transformations. These solutions mostly focused on one way to deal with information and faced more problems as they need human intervention and a large set of data. The acknowledged benefits of combining multiple types of descriptors are accompanied by challenges specially. These challenges arise due to differences in properties, such as locality and sparsity, as well as the heterogeneity exhibited by generated features. To address this issue comprehensively, we present an approach that benefits from genetic programming techniques to generate and combine two distinct texture classifiers. It incorporates histograms of oriented gradients and local binary patterns descriptors, which capture different textures. To effectively fuse the results of both classifiers, the proposed approach employs a late fusion process along with data augmentation methods while using a limited amount of training data. To evaluate the performance of the proposed approach in texture image classification tasks, we have conducted extensive experiments on six challenging datasets encompassing various variations. We have also investigated its performance in a cross dataset problem where the model has been trained on instances of a dataset before being tested on samples of another dataset. The obtained results clearly demonstrate that the proposed approach surpasses other relevant low-level approaches, as well as existing GP-based and CNN methods specifically designed for describing and classifying textures. Thanks to its ability to simultaneously leverage multiple descriptors, the suggested solution shows a high potential for real-world applications, particularly in handling various image changes with robustness.

Camera model identification based on dual-path enhanced ConvNeXt network and patches selected by uniform local binary pattern

With the rapid advancement of multimedia technologies, there is a growing demand for reliable methods to verify image integrity. Camera model identification, a passive approach aiming to determine the specific capturing device model, has garnered considerable attention in the field of source camera forensics. In this paper, we first propose a novel patch selection method that enhances the diversity of training data by utilizing the uniform local binary pattern operator to reveal spatial textual information. Secondly, we introduce a complex dual-path enhanced ConvNeXt network for camera model identification, effectively leveraging the multi-frequency information present in the image. Notably, our network demonstrates the ability to learn camera model-related features without relying on a residual prediction module. Finally, extensive experimental results on both Dresden and Vision datasets shown that the proposed network outperforms several state-of-the-art methods in both teams of identification accuracy and computational efficiency.

Scale and pattern adaptive local binary pattern for texture classification

Local binary pattern (LBP) with a fixed sampling template is sensitive to scale changes. Furthermore, under rotation changes or noise corruptions, one uniform LBP pattern can be corrupted to fall into a non-uniform pattern which loses its discrimination power to describe the corresponding texture feature. To overcome these two main drawbacks, we propose a scale and pattern adaptive local binary pattern (SPALBP). Firstly, in the gradient-based sampling radius adaptive scheme, eight directional adaptive sampling radius of each center pixel can be obtained by using its eight Kirsch gradient values. Secondly, in the noise and rotation robust neighborhood sampling scheme, three neighborhood sampling templates are used to extract three kinds of averaging neighborhood pixels. Thirdly, for each center pixel, three kinds of LBPriu2 patterns can be extracted by sampling these three kinds of averaging neighborhood pixels along eight directional adaptive sampling radius. Finally, an optimal SPALBP uniform pattern can be adaptively selected from these three LBPriu2 patterns. Hence, all SPALBP patterns show more robustness against scale changes, rotation changes and noise corruptions. Extensive experiments are conducted on four standard texture databases: Outex, UIUC, CUReT and XU_HR. Comparing with state-of-the-art LBP-based variants, the proposed SPALBP method consistently shows superior performance both in dramatic environment changes and high-levels of noise conditions, meanwhile it maintains a lower texture feature dimension.

Texture Feature Extraction from 1H NMR Spectra for the Geographical Origin Traceability of Chinese Yam.

Adulteration is widespread in the herbal and food industry and seriously restricts traditional Chinese medicine development. Accurate identification of geo-authentic herbs ensures drug safety and effectiveness. In this study, 1H NMR combined intelligent "rotation-invariant uniform local binary pattern" identification was implemented for the geographical origin confirmation of geo-authentic Chinese yam (grown in Jiaozuo, Henan province) from Chinese yams grown in other locations. Our results showed that the texture feature of 1H NMR image extracted with rotation-invariant uniform local binary pattern for identification is far superior compared to the original NMR data. Furthermore, data preprocessing is necessary. Moreover, the model combining a feature extraction algorithm and support vector machine (SVM) classifier demonstrated good robustness. This approach is advantageous, as it is accurate, rapid, simple, and inexpensive. It is also suitable for the geographical origin traceability of other geographical indication agricultural products.

Masked Graph Convolutional Network for Small Sample Classification of Hyperspectral Images

The deep learning method has achieved great success in hyperspectral image classification, but the lack of labeled training samples still restricts the development and application of deep learning methods. In order to deal with the problem of small samples in hyperspectral image classification, a novel small sample classification method based on rotation-invariant uniform local binary pattern (RULBP) features and a graph-based masked autoencoder is proposed in this paper. Firstly, the RULBP features of hyperspectral images are extracted, and then the k-nearest neighbor method is utilized to construct the graph. Furthermore, self-supervised learning is conducted on the constructed graph so that the model can learn to extract features more suitable for small sample classification. Since the self-supervised training mainly adopts the masked autoencoder method, only unlabeled samples are needed to complete the training. After training, only a small number of samples are used to fine-tune the graph convolutional network, so as to complete the classification of all nodes in the graph. A large number of classification experiments on three commonly used hyperspectral image datasets show that the proposed method could achieve higher classification accuracy with fewer labeled samples.

Face presentation attack detection performances of facial regions with multi-block LBP features.

Biometric recognition systems are frequently used in daily life although they are vulnerable to attacks. Today, especially the increasing use of face authentication systems has made these systems the target of face presentation attacks (FPA). This has increased the need for sensitive systems detecting the FPAs. Recently surgical masks, frequently used due to the pandemic, directly affect the performance of face recognition systems. Researchers design face recognition systems only from the eye region. This motivated us to evaluate the FPA detection performance of the eye region. Based on this, in cases where the whole face is not visible, the FPA detection performance of other parts of the face has also been examined. Therefore, in this study, FPA detection performances of facial regions of wide face, cropped face, eyes, nose, and mouth was investigated. For this purpose, the facial regions were determined and normalized, and texture features were extracted using powerful texture descriptor local binary patterns (LBP) due to its easy computability and low processing complexity. Multi-block LBP features are used to obtain more detailed texture information. Generally uniform LBP patterns are used for feature extraction in the literature. In this study, the FPA detection performances of both uniform LBP patterns and all LBP patterns were investigated. The size of feature vector is reduced by principal component analysis, and real/fake classification is performed with support vector machines. Experimental results on NUAA, CASIA, REPLAY-ATTACK and OULU-NPU datasets show that the use of all patterns increased the performance of FPA detection.

Micro image classification of 19 high-value hardwood species based on texture feature fusion

For classification of wood species with similar microstructure, 19 high-value hardwood species of Papilionaceae, Ebenaceae, and Caesalpiniaceae were used as experimental objects. Images of transverse sections, radial sections, and tangential sections were collected by Micro CT. Local binary patterns (LBP) are often used for feature extraction. LBP deformed forms such as uniform LBP, rotation-invariant LBP, and rotation-invariant uniform LBP were fused with Gray-Level Co-Occurrence Matrix (GLCM) to form three fusion features. The fusion features were combined with support vector machine (SVM) or BP neural network to realize wood classification. The texture feature fusion method was found to be better than the single feature classification. Among them, the effect of uniform LBP and GLCM fusion was the best, and the classification accuracy combined with SVM was the highest. The evaluation of the classification of 19 kinds of hardwood mainly depended on transverse sections, and its accuracy was higher than that of the radial and tangential sections. Therefore, the classification results of transverse sections should be taken as the main evaluation basis for the classification of the 19 high-value hardwood species.

Machine learning and uLBP histograms for posture recognition of dependent people via Big Data Hadoop and Spark platform

For dependent population, falls accident are a serious health issue, particularly in a situation of pandemic saturation of health structures. It is, therefore, highly desirable to quarantine patients at home, in order to avoid the spread of contagious diseases. A dedicated surveillance system at home may become an urgent need in order to improve the patients’ living autonomy and significantly reduce assistance costs while preserving their privacy and intimacy. The domestic fall accident is regarded as an abrupt pose transition. Accordingly, normal human postures have to be recognized first. To this end, we proposed a novel big data scalable method for posture recognition using uniform local binary pattern (uLBP) histograms for pattern extraction. Instead of saving the pixels of the entire image, only the patterns were kept for the identification of human postures. By doing so, we tried to preserve people’s intimacy, which is very important in ehealth. To our knowledge, our work is the first to use this approach in a big data platform context for fall event detection while using Random Forest instead of complex deep learning methods. Application results of our conduct are very interesting in comparison to complex architectures such as convolutional deep neural networks (CNN) and feedforward deep neural networks (DFFNN).

Flame stability measurement through image moments and texture analysis

In this article, the first two moments of the image, mean and standard deviation, uniform local binary pattern (LBP) texture analysis methods were experimentally investigated in coal-fired boilers to measure flame stability. The first two moments of the flame image were used to evaluate the flame stability in terms of color and brightness (average gray value). Although the radiation signal of the flame is widely obtained by the spectral analysis method, the radiation signal of the flame was obtained by the LBP texture analysis method in this study. The flame stability measurement technique proposed in this study does not require prior knowledge about charged coupling devices camera features. Therefore, it can be easily applied to measure flame stability without expensive and complicated adaptation processes. Flame stability was measured with R = 0.9868 accuracy with the proposed method. The experimental results show that the proposed texture analysis method is more effective than current spectral analysis methods. The results obtained within the scope of this study also show that it can be easily applied to existing closed-loop control systems to monitor flame stability.

KurdFace Morph Dataset Creation Using OpenCV

Automated facial recognition is rapidly being used to reliably identify the identities of individuals for a variety of applications, from automated border control to unlocking mobile phones. The attack of Morphing has presented a significant risk to the face recognition system (FRS) at automated border control. Face morphing is a technique for blending the facial images of two or more people such that the outcome looks like both of them. For example, a morphing attack may be used to get a fake passport by using a morphed image. This passport can be used by both the modified image contributors while crossing the border. Due to the publicly available digital altering tools that criminals may use to carry out face morphing attacks. Morph Attack Detection (MAD) systems have received a lot of attention in recent years. In the absence of automated morphing detection, Face Recognition Systems (FRS) are extremely susceptible to morphing attacks. Due to the limited number of publicly available face morph datasets to investigate, especially to our knowledge, there is no Kurdish morph dataset. In this work, we decided to generate a new face dataset, including morphed images which we named as "KurdFace" dataset. OpenCV was used to generate morphed images. Then we study the susceptibility of biometric systems to such morphed face attacks by designing and creating a Morph Attack Detection model to distinguish morphed images from genuine ones. To evaluate the robustness of our dataset regarding morphing attack detection, we compare it with the AMSL dataset to determine the classification error rate on both datasets to see how our dataset is different from others. Local Binary Pattern and Uniform Local Binary Pattern are used as feature extraction techniques, and as a classifier, SVM is utilized. The experimental result shows that our dataset is suitable for research purposes.

Concrete Bridge Crack Image Classification Using Histograms of Oriented Gradients, Uniform Local Binary Patterns, and Kernel Principal Component Analysis

Bridges deteriorate over time, which requires the continuous monitoring of their condition. There are many digital technologies for inspecting and monitoring bridges in real-time. In this context, computer vision has extensively studied cracks to automate their identification in concrete surfaces, overcoming the conventional manual methods that rely on human judgment. The general framework of vision-based techniques consists of feature extraction using different filters and descriptors and classifier training to perform the classification task. However, training can be time-consuming and computationally expensive, depending on the dimension of the features. To address this limitation, dimensionality reduction techniques are applied to extracted features, and a new feature subspace is generated. This work used histograms of oriented gradients (HOGs) and uniform local binary patterns (ULBPs) to extract features from a dataset containing over 3000 uncracked and cracked images covering different patterns of cracks and concrete surface representations. Nonlinear dimensionality reduction was performed using kernel principal component analysis (KPCA), and three machine learning classifiers were implemented to conduct the classification. The experimental results show that the classification scheme based on the support-vector machine (SVM) model and feature-level fusion of the HOG and ULBP features after KPCA application provided the best results as an accuracy of 99.26% was achieved by the proposed classification framework.

An Application of Hyperspectral Image Clustering Based on Texture-Aware Superpixel Technique in Deep Sea

This paper aims to study the application of hyperspectral technology in the classification of deep-sea manganese nodules. Considering the spectral spatial variation of hyperspectral images, the difficulty of label acquisition, and the inability to guarantee stable illumination in deep-sea environments. This paper proposes a local binary pattern manifold superpixel-based fuzzy clustering method (LMSLIC-FCM). Firstly, we introduce a uniform local binary pattern (ULBP) to design a superpixel algorithm (LMSLIC) that is insensitive to illumination and has texture perception. Secondly, the weighted feature and the mean feature are fused as the representative features of superpixels. Finally, it is fused with fuzzy clustering method (FCM) to obtain a superpixel-based clustering algorithm LMSLIC-FCM. To verify the feasibility of LMSLIC-FCM on deep-sea manganese nodule data, the experiments were conducted on three different types of manganese nodule data. The average identification rate of LMSLIC-FCM reached 83.8%, and the average true positive rate reached 93.3%, which was preferable to the previous algorithms. Therefore, LMSLIC-FCM is effective in the classification of manganese nodules.

Light field quality assessment based on aggregation learning of multiple visual features.

Light field imaging is a way to represent human vision from a computational perspective. It contains more visual information than traditional imaging systems. As a basic problem of light field imaging, light field quality assessment has received extensive attention in recent years. In this study, we explore the characteristics of light field data for different visual domains (spatial, angular, coupled, projection, and depth), study the multiple visual features of a light field, and propose a non-reference light field quality assessment method based on aggregation learning of multiple visual features. The proposed method has four key modules: multi-visual representation of a light field, feature extraction, feature aggregation, and quality assessment. It first extracts the natural scene statistics (NSS) features from the central view image in the spatial domain. It extracts gray-level co-occurrence matrix (GLCM) features both in the angular domain and in the spatial-angular coupled domain. Then, it extracts the rotation-invariant uniform local binary pattern (LBP) features of depth map in the depth domain, and the statistical characteristics of the local entropy (SDLE) features of refocused images in the projection domain. Finally, the multiple visual features are aggregated to form a visual feature vector for the light field. A prediction model is trained by support vector machines (SVM) to establish a light field quality assessment method based on aggregation learning of multiple visual features.

A Novel Covid-19 Detection System Based on PSO and Hybrid Feature Using Support Vector Machines

The world first met the coronavirus (COVID-19) in Wuhan, China in December 2019. It has continued to increase its influence from the first encounter until today. The detection of this virus, which has caused the death of many, is of great importance today. There are many approaches to the detection of this disease. One of the most effective of these approaches is the detection of COVID-19 disease using chest X-Ray images. In this paper, an intelligent system was proposed to classify normal, pneumonia patients and COVID-19 patients using chest X-Ray images. The proposed system was composed of four stage. At first, all images in the dataset were pre-processed. Then for the feature extraction uniform Local Binary Pattern (LBP) and DenseNet201 deep learning models were used. Particle swarm optimization (PSO) algorithm was used to select effective features. The determined effective features were classified by support vector machine (SVM). Accuracy and AUC parameters were used as performance criteria. Evaluated accuracy and AUC values were 99.9%, 1.00, respectively. The dataset and proposed model codes are made publicly available at: https://github.com/mfatiho/covid-detection-chest-xray

Hybrid Oriented FAST Rotated BRIEF and Non-Rotational-Invariant Uniform Local Binary Patterns for CBMIR

Hybrid Oriented FAST Rotated BRIEF and Non-Rotational-Invariant Uniform Local Binary Patterns for CBMIR

Feature Extraction Enabled Deep Learning From Specklegram for Optical Fiber Curvature Sensing

A novel approach for multimode fiber (MMF) curvature sensing based on the texture feature of the specklegram from the fiber facet is proposed, developed and demonstrated. Different from previously reported methods, the texture feature vector of the fiber specklegram is used as the descriptor of the curvature of the fiber. After the specklegrams from two kinds of MMF under different curvatures are recorded, the texture feature vector of each specklegram is first extracted using the uniform local binary pattern algorithm. Then, the texture feature vector is mapped into the target curvature in a nonlinear manner using a one-dimensional convolutional neural network (1D CNN). In the experiment, the model trained by the texture features of fiber specklegrams with a core diameter of 50 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\boldsymbol {\mu }\text{m}$ </tex-math></inline-formula> exhibits high prediction accuracy and good generalization ability in the curvature range of 1.55-6.93 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{m}^{-1}$ </tex-math></inline-formula> . In the first experiment, good recognition results are provided by the texture feature of the MMF specklegram, for which the average curvature recognition accuracy is 100%. In the second experiment, the prediction error for 91.4% of the samples in the test set is within a range of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\boldsymbol {\pm }{\mathbf {{0}.{1}\,\,m}}^{\mathbf {-{1}}}$ </tex-math></inline-formula> . In addition, this approach has significantly better prediction ability and robustness than the traditional approach, which processes the specklegram image directly using a two-dimensional convolutional neural network (2D CNN) for sensing. The experimental results demonstrate the fiber curvature sensing capability of the proposed method based on the analysis of texture feature using a 1D CNN.

Features extraction using encoded local binary pattern for detection and grading diabetic retinopathy

IntroductionReliable computer diagnosis of diabetic retinopathy (DR) is needed to rescue many with diabetes who may be under threat of blindness. This research aims to detect the presence of diabetic retinopathy in fundus images and grade the disease severity without lesion segmentation.MethodsTo ensure that the fundus images are in a standard state of brightness, a series of preprocessing steps have been applied to the green channel image using histogram matching and a median filter. Then, contrast-limited adaptive histogram equalisation is performed, followed by the unsharp filter. The preprocessed image is divided into small blocks, and then each block is processed to extract uniform local binary patterns (LBPs) features. The extracted features are encoded, and the feature size is reduced to 3.5 percent of its original size. Classifiers like Support Vector Machine (SVM) and a proposed CNN model were used to classify retinal fundus images. The classification is abnormal or normal and to grade the severity of DR.ResultsOur feature extraction method was tested on a binary classifier and resulted in an accuracy of 98.37% and 98.84% on the Messidor2 and EyePACS databases, respectively. The proposed system could grade DR severity into three grades (0: no DR, 1: mild DR, and 5: moderate, severe NPDR, and PDR). It obtains an F1-score of 0.9617 and an accuracy of 95.37% on the EyePACS database, and an F1-score of 0.9860 and an accuracy of 97.57% on the Messidor2 database. The resultant values are dependent on the selection of (neighbours, radius) pairs during the extraction of LBP features.ConclusionsThis study’s results proved that the preprocessing steps are significant and had a great effect on highlighting image features. The novel method of stacking and encoding the LBP values in the feature vector greatly affects results when using SVM or CNN for classification. The proposed system outperforms the state of the artwork. The proposed CNN model performs better than SVM.

Feature Generalization for Breast Cancer Detection in Histopathological Images.

Recent period has witnessed benchmarked performance of transfer learning using deep architectures in computer-aided diagnosis (CAD) of breast cancer. In this perspective, the pre-trained neural network needs to be fine-tuned with relevant data to extract useful features from the dataset. However, in addition to the computational overhead, it suffers the curse of overfitting in case of feature extraction from smaller datasets. Handcrafted feature extraction techniques as well as feature extraction using pre-trained deep networks come into rescue in aforementioned situation and have proved to be much more efficient and lightweight compared to deep architecture-based transfer learning techniques. This research has identified the competence of classifying breast cancer images using feature engineering and representation learning over the established and contemporary notion of using transfer learning techniques. Moreover, it has revealed superior feature learning capacity with feature fusion in contrast to the conventional belief of understanding unknown feature patterns better with representation learning alone. Experiments have been conducted on two different and popular breast cancer image datasets, namely, KIMIA Path960 and BreakHis datasets. A comparison of image-level accuracy is performed on these datasets using the above-mentioned feature extraction techniques. Image level accuracy of 97.81% is achieved for KIMIA Path960 dataset using individual features extracted with handcrafted (color histogram) technique. Fusion of uniform Local Binary Pattern (uLBP) and color histogram features has resulted in 99.17% of highest accuracy for the same dataset. Experimentation with BreakHis dataset has resulted in highest classification accuracy of 88.41% with color histogram features for images with 200X magnification factor. Finally, the results are contrasted to that of state-of-the-art and superior performances are observed on many occasions with the proposed fusion-based techniques. In case of BreakHis dataset, the highest accuracies 87.60% (with least standard deviation) and 85.77% are recorded for 200X and 400X magnification factors, respectively, and the results for the aforesaid magnification factors of images have exceeded the state-of-the-art.