LBP Features Research Articles

Human ear recognition based on local multi-scale LBP features with city-block distance

The use of the ear as a biometric modality has emerged in recent years. It makes it possible to differentiate people thanks to its stability over time and to the richness of its characteristics such as texture, color and size. This paper proposes a novel approach to ear recognition based on a variant of the Local Binary Pattern descriptor called Multi-scale Local Binary Pattern (MLBP). MLBP is calculated locally, by dividing the image into several equal blocks, to extract the ear features which will be used in the matching process to make a decision by detecting the similarities between the feature vectors using City-Block distance (CTB). The proposed method is evaluated on three reference ear databases: IIT Delhi I, IIT Delhi II and USTB-1. The analysis of the results obtained have clearly shown the robustness and the stability of the proposed ear recognition method which is highly competitive, achieving an attractive recognition performances in terms of identification rate at rank-1 up to: 98.40% for IIT Delhi I, 98.64% for IIT Delhi II, and 98.33% for USTB-1.

Recognizing gender from human facial regions using genetic algorithm

Recently, recognition of gender from facial images has gained a lot of importance. There exist a handful of research work that focus on feature extraction to obtain gender-specific information from facial images. However, analyzing different facial regions and their fusion help in deciding the gender of a person from facial images. In this paper, we propose a new approach to identify gender from frontal facial images that is robust to background, illumination, intensity, and facial expression. In our framework, first the frontal face image is divided into a number of distinct regions based on facial landmark points that are obtained by the Chehra model proposed by Asthana et al. The model provides 49 facial landmark points covering different regions of the face, e.g., forehead, left eye, right eye, lips. Next, a face image is segmented into facial regions using landmark points and features are extracted from each region. The compass LBP feature, a variant of LBP feature, has been used in our framework to obtain discriminative gender-specific information. Following this, a support vector machine-based classifier has been used to compute the probability scores from each facial region. Finally, the classification scores obtained from individual regions are combined with a genetic algorithm-based learning to improve the overall classification accuracy. The experiments have been performed on popular face image datasets such as Adience, cFERET (color FERET), LFW and two sketch datasets, namely CUFS and CUFSF. Through experiments, we have observed that, the proposed method outperforms existing approaches.

Combining GLCM with LBP features for knee osteoarthritis prediction: Data from the Osteoarthritis initiative

INTRODUCTION: Knee osteoarthritis is a chronic disease that can make a person more susceptible to develop health complications. It is a significant cause of disability among adults. In advanced stages, people can die from these complications. OBJECTIVES: This

Face Recognition across Pose using ELM Framework

This paper proposes the use of Extreme Learning Machine regression and classification framework to recognize face across pose. ELM regression framework is used to generate virtual frontal view from its corresponding side view. Kernel version of ELM is used for the non-linear mapping estimation between frontal and its corresponding non frontal view. Non Linear estimation using proposed KELM is found to be satisfactory even in the case of reduced image coefficients. In addition to regression framework, this paper also explored few popular face features like LBP, HOG, appearance and entropy features with ELM classification framework. Combination of appearance and entropy feature set is found to give best classification accuracy among the considered feature set. Proposed experiments are conducted on subset of FERET database with images up to 45° pose variation.

Comparison of HOG, MSER, SIFT, FAST, LBP and CANNY features for cell detection in histopathological images

Comparison of HOG, MSER, SIFT, FAST, LBP and CANNY features for cell detection in histopathological images

Lip Movement Feature Detection and Classification Methods

Computerized lip reading has been one of the most actively researched areas of computer vision in recent past because of its crime fighting potential and invariance to acoustic environment. However, several factors like fast speech, bad pronunciation, and poor illumination, movement of face, moustaches and beards make lip reading difficult. In present work, we propose a solution for automatic lip contour tracking and recognizing numbers 1-10 of English language spoken by speakers using the information available from lip movements. In this method first, we are detecting Face then in that ROI Lip detection. Lip movements as the only input and without using any speech recognition system in parallel. The approach used in this work is found to significantly solve the purpose of lip reading when size of database is small. In this paper also compare LBP and HOG feature with Support Vector Machine Classification. The system is use for the modern sign in PASSWORD systems.

Indoor Scene Recognition for Micro Aerial Vehicles Navigation using Enhanced-GIST Descriptors

<p>An indoor scene recognition algorithm combining histogram of horizontal and vertical directional morphological gradient features and GIST features is proposed in this paper. New visual descriptor is called enhanced-GIST. Three different classifiers, k-nearest neighbour classifier, Naïve Bayes classifier and support vector machine, are employed for the classification of indoor scenes into corridor, staircase or room. The evaluation was performed on two indoor scene datasets. The scene recognition algorithm consists of training phase and a testing phase. In the training phase, GIST, CENTRIST, LBP, HODMG and enhanced-GIST feature vectors are extracted for all the training images in the datasets and classifiers are trained for these image feature vectors and image labels (corridor-1, staircase-2 and room-3). In the test phase, GIST, CENTRIST, LBP, HODMG and enhanced-GIST feature vectors are extracted for each unknown test image sample and classification is performed using a trained scene recognition model. The experimental results show that indoor scene recognition algorithm employing SVM with enhanced GIST descriptors produces very high recognition rates of 97.22 per cent and 99.33 per cent for dataset-1 and dataset-2, compared to kNN and Naïve Bayes classifiers. In addition to its accuracy and robustness, the algorithm is suitable for real-time operations.</p>

Computer Aided Solution for Automatic Segmenting and Measurements of Blood Leucocytes Using Static Microscope Images.

Blood leucocytes segmentation in medical images is viewed as difficult process due to the variability of blood cells concerning their shape and size and the difficulty towards determining location of Blood Leucocytes. Physical analysis of blood tests to recognize leukocytes is tedious, time-consuming and liable to error because of the various morphological components of the cells. Segmentation of medical imagery has been considered as a difficult task because of complexity of images, and also due to the non-availability of leucocytes models which entirely captures the probable shapes in each structures and also incorporate cell overlapping, the expansive variety of the blood cells concerning their shape and size, various elements influencing the outer appearance of the blood leucocytes, and low Static Microscope Image disparity from extra issues outcoming about because of noise. We suggest a strategy towards segmentation of blood leucocytes using static microscope images which is a resultant of three prevailing systems of computer vision fiction: enhancing the image, Support vector machine for segmenting the image, and filtering out non ROI (region of interest) on the basis of Local binary patterns and texture features. Every one of these strategies are modified for blood leucocytes division issue, in this manner the subsequent techniques are very vigorous when compared with its individual segments. Eventually, we assess framework based by compare the outcome and manual division. The findings outcome from this study have shown a new approach that automatically segments the blood leucocytes and identify it from a static microscope images. Initially, the method uses a trainable segmentation procedure and trained support vector machine classifier to accurately identify the position of the ROI. After that, filtering out non ROI have proposed based on histogram analysis to avoid the non ROI and chose the right object. Finally, identify the blood leucocytes type using the texture feature. The performance of the foreseen approach has been tried in appearing differently in relation to the system against manual examination by a gynaecologist utilizing diverse scales. A total of 100 microscope images were used for the comparison, and the results showed that the proposed solution is a viable alternative to the manual segmentation method for accurately determining the ROI. We have evaluated the blood leucocytes identification using the ROI texture (LBP Feature). The identification accuracy in the technique used is about 95.3%., with 100 sensitivity and 91.66% specificity.

Pose-robust face recognition with Huffman-LBP enhanced by Divide-and-Rule strategy

Face recognition in harsh environments is an active research topic. As one of the most important challenges, face recognition across pose has received extensive attention. LBP feature has been used widely in face recognition because of its robustness to slight illumination and pose variations. However, due to the way of pattern feature calculation, its effectiveness is limited by the big rotations. In this paper, a new LBP-like feature extraction is proposed which modifies the code rule by Huffman. Besides, a Divide-and-Rule strategy is applied to both face representation and classification, which aims to improve recognition performance across pose. Extensive experiments on CMU PIE database, FERET database and LFW database are conducted to verify the efficacy of the proposed method. The experimental results show that our method significantly outperforms other approaches.

An expression recognition algorithm based on convolution neural network and RGB-D Images

Aiming at the problem of recognition effect is not stable when 2D facial expression recognition in the complex illumination and posture changes. A facial expression recognition algorithm based on RGB-D dynamic sequence analysis is proposed. The algorithm uses LBP features which are robust to illumination, and adds depth information to study the facial expression recognition. The algorithm firstly extracts 3D texture features of preprocessed RGB-D facial expression sequence, and then uses the CNN to train the dataset. At the same time, in order to verify the performance of the algorithm, a comprehensive facial expression library including 2D image, video and 3D depth information is constructed with the help of Intel RealSense technology. The experimental results show that the proposed algorithm has some advantages over other RGB-D facial expression recognition algorithms in training time and recognition rate, and has certain reference value for future research in facial expression recognition.

Pedestrian Detection with Improved LBP and Hog Algorithm

This article aims to improve the HOG SVM pedestrian detection method proposed by previous researchers. The speed of HOG SVM to detect pedestrians is relatively slow, and the detection accuracy is not very good. This paper proposes a PCA (principal component analysis) dimension reduction for HOG and also interpolates it. The article combines the dimensions of individual HOG features and improves their accuracy, and fuses them with improved LBP features. The features of the fusion of HOG features and LBP features can both express pedestrian profile information and obtain pedestrian texture information. This can improve the speed of pedestrian detection and improve the accuracy of detection, which is beneficial to reduce false detection and missed detection. Although some researchers have combined the two features of HOG and LBP, after simple fusion of these two features, the experimental results show that the detection effect is not much improved. This article is aimed at different formats of video detection material, an application program written on the MFC platform, making pedestrian detection of the material quickly verified, which is conducive to pedestrian detection results data analysis and recording.

Identification and classification of historical Kannada handwritten document images using LBP features

Digitisation process is very much essential for historical handwritten documents due to degraded qualities in the manuscript such as ink bleed, arbitrary geometric distortions, storage conditions and age. In this work, the age-type identification and classification of historical Kannada handwritten document images is done by applying text-block wise segmentation method, extracting the LBP features and using LDA, K-NN and SVM classifiers. The purpose of the present work is to identify the document script of the dynasties, whether it belongs to Hoysala dynasty or Vijayanagara dynasty or Mysore Wodeyar's dynasty? The average classification accuracy of the proposed method with LDA classifier is 94.6%, whereas K-NN classifier yielded 98.3% and SVM classifier yielded 99.3%. As per the results obtained from the experimentation, it is proved that the SVM classifier has got good classification ability comparatively with respect to LDA and K-NN classifiers for historical Kannada handwritten document images of all age-type scripts.

Identification and classification of historical Kannada handwritten document images using LBP features

Digitisation process is very much essential for historical handwritten documents due to degraded qualities in the manuscript such as ink bleed, arbitrary geometric distortions, storage conditions and age. In this work, the age-type identification and classification of historical Kannada handwritten document images is done by applying text-block wise segmentation method, extracting the LBP features and using LDA, K-NN and SVM classifiers. The purpose of the present work is to identify the document script of the dynasties, whether it belongs to Hoysala dynasty or Vijayanagara dynasty or Mysore Wodeyar's dynasty? The average classification accuracy of the proposed method with LDA classifier is 94.6%, whereas K-NN classifier yielded 98.3% and SVM classifier yielded 99.3%. As per the results obtained from the experimentation, it is proved that the SVM classifier has got good classification ability comparatively with respect to LDA and K-NN classifiers for historical Kannada handwritten document images of all age-type scripts.

基于改进纹理特征的红外目标跟踪算法

基于改进纹理特征的红外目标跟踪算法

Parallel deep solutions for image retrieval from imbalanced medical imaging archives

Learning and extracting representative features along with similarity measurements in high dimensional feature spaces is a critical task. Moreover, the problem of how to bridge the semantic gap, between the low-level information captured by a machine learning model and the high-level one interpreted by a human operator, is still a practical challenge, especially in medicine. In medical applications, retrieving similar images from archives of past cases can be immensely beneficial in diagnostic imaging. However, large and balanced datasets may not be available for many reasons. Exploring the ways of using deep networks, for classification to retrieval, to fill this semantic gap was a key question for this research. In this work, we propose a parallel deep solution approach based on convolutional neural networks followed by a local search using LBP, HOG and Radon features. The IRMA dataset, from ImageCLEF initiative, containing 14,400 X-ray images, is employed to validate the proposed scheme. With a total IRMA error of 165.55, the performance of our scheme surpasses the dictionary approach and many other learning methods applied on the same dataset.

Feature fusion with covariance matrix regularization in face recognition

The fusion of multiple features is important for achieving state-of-the-art face recognition results. This has been proven in both traditional and deep learning approaches. Existing feature fusion methods either reduce the dimensionality of each feature first and then concatenate all low-dimensional feature vectors, named as DR-Cat, or the vice versa, named as Cat-DR. However, DR-Cat ignores the correlation information between different features which is useful for classification. In Cat-DR, on the other hand, the correlation information estimated from the training data may not be reliable especially when the number of training samples is limited. We propose a covariance matrix regularization (CMR) technique to solve problems of DR-Cat and Cat-DR. It works by assigning weights to cross-feature covariances in the covariance matrix of training data. Thus the feature correlation estimated from training data is regularized before being used to train the feature fusion model. The proposed CMR is applied to 4 feature fusion schemes: fusion of pixel values from 3 color channels, fusion of LBP features from 3 color channels, fusion of pixel values and LBP features from a single color channel, and fusion of CNN features extracted by 2 deep models. Extensive experiments of face recognition and verification are conducted on databases including MultiPIE, Georgia Tech, AR and LFW. Results show that the proposed CMR technique significantly and consistently outperforms the best single feature, DR-Cat and Cat-DR.

Research and implementation of target tracking algorithm in compression domain on miniaturized DSP platform

The target tracking algorithm in compression domain based on compression perception is studied. To meet the specific application requirements, the shortcomings of original algorithm are improved. At the same time, based on the design idea and demand of miniaturized target position detector, a real-time image processing platform with TMS320DM6437 digital signal processor as the core is designed and implemented, and the algorithm is im-plemented and optimized on the DSP platform. The simulation and experiment results show that after the combination of Kalman filter, LBP feature and adding adaptive learning rate update strategy, the stability of the algorithm is improved. For the implementation in DSP, after a series of optimizing measures, as for an image with resolution of 960×960, taking the target window of 80×80 into account, the computation speed can be up to 25 fps, which can meet the requirement of real-time tracking. The embedded tracking system can track the selected moving objects continuously and stably, and can meet the target localization and tracking requirements under specific applications, which has a real practical value. Moreover, the method in this paper has a certain reference value for the research and applications of this kind of target tracking method in the embedded platform.

Haar-Like Multi-Granularity Texture Features for Pedestrian Detection

Pedestrian detection has been a significant problem for decades and remains a hot topic in computer vision. Pedestrian detection is one of the key algorithms for self-driving cars and some other functions in robotics, including driver support systems, road surveillance systems. In this paper, based on the characteristics of the human body and the Haar feature, the Haar-like multi-granularity local texture feature, i.e., multi-granularity Haar-like LBP (mgh-LBP), is proposed for pedestrian detection. The mgh-LBP feature combines four characteristics of the human body and their backgrounds to construct the Haar-like features, which can better describe human body texture and edge information. Compared with other texture features, including the rotation-invariant LBP feature, uniform LBP feature and basic-LBP feature, the proposed method greatly reduces the feature dimension and computational complexity, and obtains a higher pedestrian detection rate and robust detection performance.

Face Recognition LBP Feature Extraction and PCA Techniques

Face recognition is one of the security methods in biometric system in world wide area. Different mathematical calculations are used to perform face recognition. In this paper, Linear Binary pattern is applied to the different ORL face database. Linear discriminant analysis is applied followed by linear binary pattern. In this, different component analysis and training set data reduction is done by PCA techniques. The Feature extraction & pattern recognition is done by LBP method. The classification rate is achieved up to 94.7

A membrane-inspired bat algorithm to recognize faces in unconstrained scenarios

Face recognition under unconstrained environments has become increasingly important due to the broad prospect in real-world applications. In order to counter uncertainties imposed by faces captured in such unconstrained imaging situations, a robust, discriminative and computationally efficient feature selection scheme is of paramount significance. In this regard, bio-inspired feature selection methods have been exploited due to their sophisticated ability, flexibility and adaptability. However, their performances tend to deteriorate severely in large-scale domains such as face recognition due to the premature convergence problem. In this paper, high-dimensional LBP features are extracted from face images and fused with Gabor wavelet features using Canonical Correlation Analysis (CCA). To further enhance the discrimination power of the facial representation and to alleviate the curse of dimensionality, a novel membrane-inspired feature selection approach is proposed, where a Binary Bat Algorithm (BBA) under the framework of Membrane Computing (MC) is employed. Inherent parallelism and non-determinism are two distinguishing characteristics of MC that can help in maintaining the diversity of population and balancing the exploration–exploitation trade-off. In the proposed membrane-inspired BBA (MIBBA), the structure as well as the evolution, dissolution and communication rules of MC are integrated into the BBA to enhance the trajectories of bats. Furthermore, the Great Deluge Algorithm (GDA), is integrated into the skin membrane to further improve its exploitation ability. Experimental results show that the proposed approach yields competitive recognition rates and outperforms well-known state-of-the-art methods on three benchmark databases (AR, LFW and GBU). Further experimental evaluations justify the ability of the proposed approach to handle the small sample size problem.