Multi-scale Local Binary Pattern Research Articles

Hyperdimensional Computing with Multi-Scale Local Binary Patterns for Scalp EEG-Based Epileptic Seizure Detection

Hyperdimensional Computing with Multi-Scale Local Binary Patterns for Scalp EEG-Based Epileptic Seizure Detection

Construction of college music information teaching mode under the background of Internet

Abstract The traditional music teaching method in the informationization era has been difficult to adapt to the needs of modern teaching and must be reformed in the direction of informationization. In this paper, based on the closure, inflection point and outer enclosing box features of the stroke line element, the recognition of handwritten notes is carried out from the three categories of straight line segments, folded line segments and quadratic curves. Meanwhile, for the binarized music score image, the multi-directional LBP features for spectral line detection are improved, and the computation method of multi-scale spectral line detection LBP features is established. The Manhattan distance is used to evaluate and select the features, which are inputted into XGBoost for classification and recognition training based on the statistical distribution characteristics of the features. Note recognition and spectral line recognition are applied to college music teaching, and the effectiveness of teaching is explored. In the rhythm-recognition path, the recognition teaching based on multi-scale and multi-directional LBP features led to an increase in students’ mastery of the musical score by 2.8 and in the phrasing and segmentation path by 3.5. Informational teaching led to a deepening of students’ mastery of the notes and musical scores.

Local binary pattern and its derivatives to handwriting-based gender classification

Several studies by psychologists and computer scientists have verified the link between handwriting and writer gender. The texture of the writing image is a major indicator of whether it is male or female writing. This paper conducts a comparison analysis to examine the effectiveness of various local binary patterns (LBPs) techniques in detecting gender from scanned images of handwriting. We study different LBP variants, including complete local binary pattern (CLBP), local ternary pattern (LTP), local configuration pattern (LCP), rotated local binary pattern (RLBP), local binary pattern variance (LBPV), and multi-scale local binary pattern (MLBP), as features for representing handwriting images. A support vector machine (SVM) is trained using features from male and female writing. The method achieves encouraging classification rates of 76.68 when tested on subsets of the Qatar University writer identification (QUWI) dataset containing English and Arabic writing samples when using the experimental protocols of the International Conference on Document Analysis and Recognition (ICDAR) 2013 gender classification competitions.

Multi-scale LBP fusion with the contours from deep CellNNs for texture classification

In texture classification, local binary pattern (LBP) is currently one of the most widely-concerned feature encoding models. Most existing LBP-based texture classification methods are usually limited to single-kind texture features. In fact, an across-domain fusion of LBP features with other features, such as image contours, could be another potential path to promote texture classification. To enhance the feature modeling ability of LBP-based methods, this paper firstly designs a Cellular Neural Network (CellNN) with recurrent convolutions, initially trained by a simplified simulated-annealing algorithm, to extract informative image contours. For better reliability, a new three-channel contour extractor of deep CellNNs (i.e., dCellNNs) is proposed. This extractor contains the initially-trained CellNNs of more than three layers, and it is further optimized by fine-tuning parameters. Moreover, a new weighted-base algorithm is designed to fulfill the fusion of the multi-scale texture features by LBPs and the contour features by dCellNNs to enhance feature representation. Finally, these enhanced features are concatenated together to generate the final multi-scale features of given texture image. On texture datasets KTH, Brodatz, OTC12 and UIUC, experiment results verify that the across-domain fusion of multi-scale LBPs and dCellNNs is efficient in capturing & enhancing texture features. With moderate feature dimensionality and computational costs, it could improve texture classification, acquiring an obvious accuracy increase on previous state-of-the-art ones, e.g., a rise of 2.58% on KTH-TIPS2b, a rise of 3.11% on Brodatz, a rise of 0.71% on OTC12 and a rise of 0.42% on UIUC.

Fault diagnosis of driving gear in rack and pinion drives based on multi-scale local binary pattern extraction and sparse representation

Rack and pinion drives (RPDs) are key components of battery-swapping systems (BSSs) used in electric heavy trucks; the faults occurring in these drives reduce the efficiency, accuracy, quality of battery swapping, and even pose potential safety risks. The operating conditions of RPD driving gear in BSSs are characterized by speed fluctuations, relatively low speeds, and reciprocating motion. To assess the driving gear fault characteristics under these conditions, based on the solution of image recognition under complex and low illumination conditions, this study proposes a fault diagnosis framework that includes adaptive down-sampling, three-dimensional acceleration data fusion, multi-scale local binary pattern (MS-LBP) extraction, and sparse representation. First, adaptive down-sampling is used to smooth out the speed fluctuation. Subsequently, MS-LBP extraction is employed to obtain efficient fault features at low speed. Finally, dictionary learning and sparse representations are conducted on the MS-LBP features. The effectiveness and advantages of the proposed diagnosis approach are demonstrated using monitoring data acquired from a BSS. Moreover, comparative studies demonstrate that the proposed fault diagnosis method yields improved performance.

Multiattention Joint Convolution Feature Representation With Lightweight Transformer for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is currently a hot topic in the field of remote sensing. The goal is to utilize the spectral and spatial information from HSI to accurately identify land covers. Convolution neural network (CNN) is a powerful approach for HSI classification. However, CNN has limited ability to capture non-local information to represent complex features. Recently, vision transformers (ViTs) have gained attention due to their ability to process non-local information. Yet, under the HSI classification scenario with ultra-small sample rates, the spectral-spatial information given to ViTs for global modeling is insufficient, resulting in limited classification capability. Therefore, in this article, Multi-Attention Joint Convolution Feature Representation with Lightweight Transformer (MAR-LWFormer) is proposed, which effectively combines the spectral and spatial features of HSI to achieve efficient classification performance at ultra-small sample rates. Specifically, we use a three-branch network architecture to extract multi-scale convolved 3D-CNN, EMAP, and LBP features of HSI, respectively, by taking full exploitation of ultra-small training samples. Second, we design a series of multi-attention modules to enhance spectral-spatial representation for the three types of features and to improve the coupling and fusion of multiple features. Third, we propose an explicit feature attention tokenizer to transform the feature information, which maximizes the effective spectral-spatial information retained in the flat tokens. Finally, the generated tokens are input to the designed lightweight transformer for encoding and classification. Experimental results on three datasets validate that MAR-LWFormer has an excellent performance in HSI classification at ultra-small sample rates when compared to several state-of-the-art classifiers.

Ghost-Free Multi-Exposure Image Fusion Technology Based on the Multi-Scale Block LBP Operator

This paper proposes a ghost-free multi-exposure image fusion technique based on the multi-scale block LBP (local binary pattern) operator. The method mainly includes two steps: first, the texture variation, brightness, and spatial consistency weight maps of the image are computed, and then these three image features are used to construct the initial weight map. Finally, the multi-resolution method is used to fuse the images to obtain the resulting image. The main advantage of this technique lies in the step of extracting the details of the source image based on the multi-scale block LBP operator, which is used to preserve the details of the brightest and darkest areas in high dynamic range scenes and preserve the texture features of the source image. Another advantage is that a new LBP operator-based motion detection method is proposed for fusing multi-exposure images in dynamic scenes containing moving objects. In addition, this paper also studies two spatially consistent weight distribution methods and compares and discusses the effects of these two methods on the results of dynamic image fusion. Through a large number of experimental comparisons, the superiority and feasibility of this method are proved.

Multi-Scale LBP Texture Feature Learning Network for Remote Sensing Interpretation of Land Desertification

Land desertification is a major challenge to global sustainable development. Therefore, the timely and accurate monitoring of the land desertification status can provide scientific decision support for desertification control. The existing automatic interpretation methods are affected by factors such as “same spectrum different matter”, “different spectrum same object”, staggered distribution of desertification areas, and wide ranges of ground objects. We propose an automatic interpretation method for the remote sensing of land desertification that incorporates multi-scale local binary pattern (MSLBP) and spectral features based on the above issues. First, a multi-scale convolutional LBP feature extraction network is designed to obtain the spatial texture features of remote sensing images and fuse them with spectral features to enhance the feature representation capability of the model. Then, considering the continuity of the distribution of the same kind of ground objects in local space, we designed an adaptive median filtering method to process the probability map of the extreme learning machine (ELM) classifier output to improve the classification accuracy. Four typical datasets were developed using GF-1 multispectral imagery with the Horqin Left Wing Rear Banner as the study area. Experimental results on four datasets show that the proposed method solves the problem of ill classification and omission in classifying the remote sensing images of desertification, effectively suppresses the effects of “homospectrum” and “heterospectrum”, and significantly improves the accuracy of the remote sensing interpretation of land desertification.

Hybrid approach to Content-Based Image Retrieval using modified multi-scale LBP and color features

The objective of the Content-Based Image Retrieval (CBIR) system is to retrieve the visually identical images from the database efficiently and effectively. It is a broad research realm with the availability of numerous applications. Performance dependency of CBIR focuses on the extraction, reduction, and selection of the features along with the practice of classification technique. In this work, we have proposed the hybrid approach of two different feature descriptors namely, Global Color Histogram and Multi-Scale Local Binary Pattern (MS-LBP). Furthermore, PCA is used for dimension reduction and LDA for the selection of features. The proposed method is evaluated concerning various benchmark datasets namely Corel-1k, Corel-5k, Corel-10k, and Ghim-10k, and results are compared based on precision and recall values at different thresholds. Euclidean distance and City Block distance are used for classification purposes. The performance study of the proposed work displays it as outperformer than the identified literature methods.

Facial Makeup Detection Using Multi-Scale Local Binary Patterns and Convolutional Neural Network Fusion

This study presents a novel facial makeup detection scheme using fusion of multi-scale Local Binary Patterns (ms-LBP) texture methods and convolutional neural network (CNN) deep learning extractor. Facial makeups affect the accuracy of face recognition systems due to appearance alteration of individuals. In order to fuse the facial features, the proposed scheme first considers concatenation of extracted global histogram of a whole image using three different LBP operators. The LBP scales are used to extract and then concatenate the local histogram of overlapping and nonoverlapping blocks of images. This way utilizes the advantages of microtexton information of local primitives besides the extracted global textures. Finally, the extracted features using CNN feature extractor are combined with global and local multi-scale textures. In general, CNN deep learning extractor learns high-level discriminative characteristics of images and therefore the proposed system improves the facial makeup detection rate by involving both microtexton and discriminative information of facial images. In addition, the proposed method attempts to select the optimized subset of facial features to increase the detection performance of system by applying Particle Swarm Optimization (PSO) technique after feature level fusion. The paper uses Support Vector Machine (SVM) classifier for classifying the facial vectors into makeup or no-makeup classes. The proposed scheme is then evaluated using YMU, VMU and MIW facial makeup databases with consideration of light, medium and heavy makeups on several datasets. Experimental results analysis clarifies the effectiveness of proposed facial makeup detection framework of this study.

Tree trunk texture classification using multi-scale statistical macro binary patterns and CNN

Automated plant classification using tree trunk has attracted increasing interest in the computer vision community as a contributed solution for the management of biodiversity. It is based on the description of the texture information of the bark surface. The multi-scale variants of the local binary patterns have achieved prominent performance in bark texture description. However, these approaches encode the scale levels of the macrostructure separately from each other. In this paper, a novel handcrafted texture descriptor termed multi-scale Statistical Macro Binary Patterns (ms-SMBP) is proposed to encode the characterizing macro pattern of different bark species. The proposed approach consists of defining a sampling scheme at high scale levels and summarizing the intensity distribution using statistical measures. The characterizing macro pattern is encoded by an in-depth gradient that describes the relationship between the scale levels and their adaptive statistical prototype. Besides this handcrafted feature descriptor, a learning-based description is performed with the ResNet34 model for bark classification. Extensive and comprehensive experiments on challenging and large-scale bark datasets demonstrate the effectiveness of ms-SMBP to identify bark species and outperforming different multi-scale LBP approaches. The tree trunk classification with ResNet34 shows interesting results on a very large-scale dataset.

An Early Prediction of Tumor in Heart by Cardiac Masses Classification in Echocardiogram Images Using Robust Back Propagation Neural Network Classifier

Identification and classification of intracardiac masses in echocardiogram is one of the significant processes in the diagnosis of cardiovascular disease. A robust back propagation neural network (RBPNN) technique is used to conquer every single conventional-issue utilizing the echocardiogram image analysis for this work, which consists of four phases such as noise removal, automatic segmentation, feature extraction, and intracardiac masses classification. Initially, the noise is diminished from the echocardiogram images utilizing the adaptive vector median filter (AVMF). Then, linear iterative vessel segmentation (LIVS) is applied for automatic segmentation of the masses followed by the extraction of texture features using the multiscale local binary pattern (MS-LBP) approach. Finally, RBPNN is employed to classify the heart mass from the images of echocardiogram with the layered kernel for the system combination. Extensive simulation results obtained using proposed AVMF-MS-LBP based RBPNN approach disclosed the superiority over existing intracardiac mass detection and classification approaches in terms of accuracy of 98.85%.

A multimodal architecture using Adapt‐HKFCT segmentation and feature‐based chaos integrated deep neural networks (Chaos‐DNN‐SPOA) for contactless biometricpalm vein recognition system

In the recent past, the fusion of various unimodal biometrics has gained increasing attention from researchers dedicated to the use of practical biometrics. In this paper, a Chaos Integrated Deep Neural Networks (Chaos-DNN) using Sandpiper Optimization Algorithm (SPOA) is proposed to enhance the performance of the multimodal contactless biometric pattern recognition system. The most significant advantage of palm vein and palm dorsal vein recognition is that it provides relatively high accuracy, reliability and also liveness detection. In this recognition process, the palm and its dorsal vein images are segmented using multilevel segmentation of region of interest (ROI) depending on Adaptive Hyper Kernel Optimized Fuzzy Clustering Technique (Adapt-HKFCT), and then ROI extracted based on the valley points among the index and ring finger using the Knuckle points. Then, the features of the ROI amid the index and ring finger are extracted using centre-symmetric local binary pattern algorithm and fed to the Chaos-DNN for training and classification. The efficiency of the features is optimized using SPOA. The extracted feature points help in authenticating a person using his/her chosen biometric traits for security purposes. The objective of this system is to increase the efficiency of the biometric system, and the performance is calculated depending on equal error rate, correct recognition rate, decidability index, false acceptance rate and false rejection rate. The proposed algorithm has been implemented in MATLAB platform. The experimental outcomes demonstrate that the proposed palm vein recognition depending Adapt-HKFCT with Chaos-DNN using SPOA method (PVR-AHKFCT-CDNN-SPOA) attains higher performance metrics with an accuracy of 98.3% and is also more efficient likened to the other existing methods, such as K Nearest Neighbour with Particle Swarm Optimization (PVR-KNN-PSO), Fuzzy Brain Storm Optimization based on Adaptive Thresholding (PVR-FBSO-AT), multiscale local binary pattern with ant colony optimization (PVR-MSLBP-ACO) and Deep Learning with Bayesian Optimization (PVR-DL-BO).

Spectral-Spatial Hyperspectral Image Semisupervised Classification by Fusing Maximum Noise Fraction and Adaptive Random Multigraphs

Hyperspectral images (HSIs) contain large amounts of spectral and spatial information, and this provides the possibility for ground object classification. However, when using the traditional method, achieving a satisfactory classification result is difficult because of the insufficient labeling of samples in the training set. In addition, parameter adjustment during HSI classification is time-consuming. This paper proposes a novel fusion method based on the maximum noise fraction (MNF) and adaptive random multigraphs for HSI classification. Considering the overall spectrum of the object and the correlation of adjacent bands, the MNF was utilized to reduce the spectral dimension. Next, a multiscale local binary pattern (LBP) analysis was performed on the MNF dimension-reduced data to extract the spatial features of different scales. The obtained multiscale spatial features were then stacked with the MNF dimension-reduced spectral features to form multiscale spectral-spatial features (SSFs), which were sent into the RMG for HSI classification. Optimal performance was obtained by fusion. For all three real datasets, our method achieved competitive results with only 10 training samples. More importantly, the classification parameters corresponding to different hyperspectral data can be automatically optimized using our method.

No-reference Image Quality Assessment of Underwater Images Using Multi-Scale Salient Local Binary Patterns

Images acquired in underwater scenarios may contain severe distortions due to light absorption and scattering, color distortion, poor visibility, and contrast reduction. Because of these degradations, researchers have proposed several algorithms to restore or enhance underwater images. One way to assess these algorithms’ performance is to measure the quality of the restored/enhanced underwater images. Unfortunately, since reference (pristine) images are often not available, designing no-reference (blind) image quality metrics for this type of scenario is still a challenge. In fact, although the area of image quality has evolved a lot in the last decades, estimating the quality of enhanced and restored images is still an open problem. In this work, we present a no-reference image quality evaluation metric for enhanced underwater images (NR-UWIQA) that uses an adapted version of the multi-scale salient local binary pattern operator to extract image features and a machine learning approach to predict quality. The proposed metric was tested on the UID-LEIA database and presented good accuracy performance when compared to other state-of-the-art methods. In summary, the proposed NR-UWQIA method can be used to evaluate the results of restoration techniques quickly and efficiently, opening a new perspective in the area of underwater image restoration and quality assessment.

CamNav: a computer-vision indoor navigation system

We present CamNav, a vision-based navigation system that provides users with indoor navigation services. CamNav captures images in real time while the user is walking to recognize their current location. It does not require any installation of indoor localization devices. In this paper, we describe the techniques of our system that improve the recognition accuracy of an existing system that uses oriented FAST and rotated BRIEF (ORB) as part of its location-matching procedure. We employ multiscale local binary pattern (MSLBP) features to recognize places. We implement CamNav and conduct required experiments to compare the obtained accuracy when using ORB, the scale-invariant feature transform (SIFT), MSLBP features, and the combination of both ORB and SIFT features with MSLBP. A dataset composed of 42 classes was constructed for assessment. Each class contains 100 pictures designed for training one location and 24 pictures dedicated for testing. The evaluation results demonstrate that the place recognition accuracy while using MSLBP features is better than the accuracy when using SIFT features. The accuracy when using SIFT, MSLBP, and ORB features is 88.19%, 91.27%, and 96.33%, respectively. The overall accuracy of recognizing places increased to 93.55% and 97.52% after integrating MSLBP with SIFT with ORB, respectively.

2D-LCoLBP: A Learning Two-Dimensional Co-Occurrence Local Binary Pattern for Image Recognition.

The rotation, scale and translation invariance of extracted features have a high significance in image recognition. Local binary pattern (LBP) and LBP-based descriptors have been widely used in image recognition due to feature discrimination and computational efficiency. However, most of the existing LBP-based descriptors have been designed to achieve rotation invariance while fail to achieve scale invariance. Moreover, it is usually difficult to achieve a good trade-off between the feature discrimination and the feature dimension. In this work, a learning 2D co-occurrence LBP termed 2D-LCoLBP is proposed to address these issues. Firstly, a weighted joint histogram is constructed in different neighborhoods and scales of an image to represent the multi-neighborhood and multi-scale LBP (2D-MLBP) and achieve the rotation invariance. A feature learning strategy is then designed to learn the compact and robust descriptor (2D-LCoLBP) from LBP pattern pairs across different scales in the extracted 2D-MLBP to characterize the most stable local structures and achieve the scale invariance, as well as decrease the feature dimension and improve the noise robustness. Finally, a linear SVM classifier is employed for recognition. We applied the proposed 2D-LCoLBP on four image recognition tasks-texture, object, face and food recognition with ten image databases. Experimental results show that 2D-LCoLBP has obviously low feature dimension but outperforms the state-of-the-art LBP-based descriptors in terms of recognition accuracy under noise-free, Gaussian noise and JPEG compression conditions.

Weighted Multi-scale Local Binary Pattern Histograms for Face Recognition

This paper proposes a novel face recognition methodology, which is based on the combination of the texture operator, namely Multi-scale Local Binary Pattern (MSLBP), face image filtering and discriminative feature weighting algorithms. Presented MSLBP principle enhances the discriminative power of the original Local Binary Pattern operator. The combination of the MSLBP and low-pass filtering improves the stability of the feature vector for different scales of the input face. Proposed mini-batch discriminative feature weighting methodologies are applied to the feature space in the feature and block levels in order to enhance the components more relevant to the recognition process. The observed PCA based data compression algorithm significantly reduced the dimensionality of the feature vector with a minimal loss in the precision of the recognition process. The identification precision exceeded the threshold of 99% for the frontal subsets of a color FERET database.

An Efficient Retinal Vessels Biometric Recognition System by Using Multi-Scale Local Binary Pattern Descriptor

Biometric systems are technically used for human recognition by identifying the unique features of an individual. Many security issues are found related to biometric systems such as voice, fingerprints, face, iris, signatures, etc., but the retina is a unique and efficient method to identify valid one. The aim of this paper is provided with an efficient method to recognize someone based on unique retina features. A proposed system based on retinal blood vessel pattern by using multi-scale local binary pattern (MSLBP) and random forest (Bagging tree) as feature extraction and classification. MSLBP is an efficient method to extracted features at six scales perpixel level, earlier work found the deficiency based on simple binary pattern with coverage of small areas and per-pixel level in the surrounding. MSLBP and random forest classifier suggested approach use for improving usability, perceivability, and sensitivity on large scale areas. It is the fastest method to get features accurately in an efficient way at every level of pixels. This method based on deep learning evaluation (criteria) parameter selection that provides more significant influence with sharp feature extraction on large scale areas based on seconds and improves the efficiency of images. MSLBP overcomes the problem of image sizing, pixel levels and efficiently provide accurate results.

Hybrid Approach to Content-Based Image Retrieval Using Modified Multi-Scale LBP and Color Features

The objective of the content-based image retrieval (CBIR) system is to retrieve the visually identical images from the database efficiently and effectively. It is a broad research realm with the availability of numerous applications. Performance dependence of CBIR focuses on the extraction, reduction, and selection of the features along with the practice of classification technique. In this work, we have proposed the hybrid approach of two different feature descriptors: global color histogram and multi-scale local binary pattern (MS-LBP); furthermore, the use of PCA for dimension reduction and LDA for the selection of features. The proposed method is evaluated concerning various benchmark datasets, viz., Corel-1k, Corel-5k, Corel-10k, and Ghim-10k together with result comparison based on the precision and recall values at different thresholds. The classification purposes are satisfied with Euclidean and City Block distance. The performance study of the proposed work displays it as outperformer than the identified state-of-the-art literature.