Local Binary Pattern Feature Extraction Research Articles

A learning framework for shape retrieval based on multilayer perceptrons

With the rapid development of 3D technology, the demand to use and retrieve 3D models has become increasingly urgent. In this paper, we present a framework that consists of a sketch-based local binary pattern (SBLBP) feature extraction method, a learning algorithm for the best view of a shape based on multilayer perceptrons (MLPs) and a learning method for shape retrieval based on two Siamese MLP networks. The model is first projected into many multiview images. A transfer learning scheme based on graphic traversal to identify Harris key points is proposed to build relations between view images and sketches. In addition, an MLP classifier is used for classification to obtain the best views of each model. Moreover, we propose a new learning method for shape retrieval that simultaneously uses two Siamese MLP networks to learn SBLBP features. Furthermore, we build a joint Bayesian method to fuse the outputs of the views and sketches. Based on training with many samples, the MLP parameters are effectively fit to perform shape retrieval. Finally, an experiment is conducted to verify the feasibility of the approach, and the results show that the proposed framework is superior to other approaches.

Intuitionistic fuzzy local binary pattern for features extraction

We propose a novel intuitionistic fuzzy feature extraction method to encode local texture. The proposed method extends the fuzzy local binary pattern approach by incorporating intuitionistic fuzzy set theory in the representation of local patterns of texture in images. Intuitionistic fuzzy local binary pattern also contribute to more than one bin in the distribution of the intuitionistic fuzzy local binary pattern values which can be used as a feature vector. The proposed intuitionistic fuzzy local binary pattern approach was experimentally evaluated for Lena image of the size 256 × 256. The results validate the effectiveness of the proposed intuitionistic fuzzy local binary pattern over the local binary pattern and fuzzy local binary pattern feature extraction methods.

Secure Image LBP Feature Extraction in Cloud-Based Smart Campus

The smart campus can monitor students in real time by analyzing students’ images, but a large number of images bring an unbearable burden to the smart campus. The convenience of cloud computing has attracted smart campus to outsource their huge amount of data to cloud servers. Although the outsourcing of data can reduce the computational and storage burden on smart campus, the privacy preserving becomes the biggest concern. This issue has attracted many researchers to study the protection of outsourced multimedia data. In this paper, we propose an effective and practical privacy-preserving computation outsourcing protocol for the local binary pattern (LBP) feature over huge encrypted images. The image owner uploads the encrypted version of images to the cloud. The cloud server takes the responsibility of extracting the LBP features from encrypted images for various applications. In the encryption process, an image is divided into non-overlapping blocks at first, and the blocks are shuffled to protect the image content. Next, all the non-center pixels in each block are shuffled. Finally, the pixels are encrypted by splitting the original image data randomly. When such an encrypted image is received, the cloud servers can calculate the LBP features by secure multiparty computation. The extracted features can be applied to many applications, such as texture classification, image retrieval, face recognition, and so on.

Automatic classification of colorectal and prostatic histologic tumor images using multiscale multispectral local binary pattern texture features and stacked generalization

This paper proposes a new multispectral multiscale local binary pattern feature extraction method for automatic classification of colorectal and prostatic tumor biopsies samples. A multilevel stacked generalization classification technique is also proposed and the key idea of the paper considers a grade diagnostic problem rather than a simple malignant versus tumorous tissue problem using the concept of multispectral imagery in both the visible and near infrared spectra. To validate the proposed algorithm performances, a comparative study against related works using multispectral imagery is conducted including an evaluation on three different multiclass datasets of multispectral histology images: two representing images of colorectal biopsies - one dataset was acquired in the visible spectrum while the second captures near-infrared spectra. The proposed algorithm achieves an accuracy of 99.6% on the different datasets. The results obtained demonstrate the advantages of infrared wavelengths to capture more efficiently the most discriminative information. The results obtained show that our proposed algorithm outperforms other similar methods.

CBIR of Brain MR Images Using Histogram of Fuzzy Oriented Gradients and Fuzzy Local Binary Patterns

Retrieval of similar images from large dataset of brain images across patients would help the experts in the decision diagnosis process of diseases. Generally used feature extraction methods are color, texture and shape. In medical images texture and shape features are most efficient. Histogram of Oriented Gradients (HOG) and Local Binary Pattern (LBP) are good descriptor for brain MR image retrieval. But there are many challenges facing in medical application. An empirical study of the impact of increasing bins number in the HOG descriptor concluded that larger the number is more accurate the descriptor is. In fact this is due to the reduction of orientations range that each bin covers. Despite the efficiency of augmenting the bins number, this technique has limited spatial support as the augmentation of the number of bins used leads to increase the histogram dimension. So here proposed a method called Histogram of Fuzzy Oriented Gradients (HFOG), in which a pixel can belong several bins with different degrees. The Local Binary Patterns feature extraction method is widely used for texture analysis; however, the original LBP is based on hard thresholding the neighborhood of each pixel. Therefore, texture representation with LBP is very sensitive to noise and cannot distinguish between a strong and a weak pattern. In this study, Fuzzy Local Binary Patterns was introduced to improve the original LBP.

Classification of breast tissues into mass and non-mass by means of the micro-genetic algorithm, phylogenetic trees, LBP and SVM

This work has the objective of developing a methodology for the classification of regions of interest (ROI) extracted from mammograms into masses and non-masses. To this end, we conducted a comparative study by combining several techniques in the various stages of the problem. We compared several texture-based techniques for the classification of ROIs. This study combines image processing, phylogenetic trees (PT), local binary patterns (LBP), support vector machines (SVM) and the micro-genetic algorithm (GA). The analysis of texture is performed, either through the combination PT/LBP or with grey levels, to compute the taxonomic diversity () and taxonomic distinction (*) indexes extracted from sub-regions (circular, circular crown, internal mask, external mask and the combination of internal and external mask) of an ROI. A GA is used to estimate the best phylogenetic weights. Then, its results are compared with the results achieved with the use of PT only. We also analyse the behaviour of the methodology when using the ROIs with and without enhancement. This enhancement consists of the application of a mean filter and the contrast-limited adaptive histogram equalisation (CLAHE). PTs and SVM were used to perform the selection of features. To evaluate the performance of the methodologies under analysis, we used the following metrics: sensitivity, specificity, accuracy and area under the receiver operating characteristic (ROC) curve (). Sensitivity and specificity measure the efficiency of the classifier at the correct detection of positive (masses) and negative (non-masses) cases, respectively. Accuracy measures the performance of the classification in both cases. The ROC curve is the graphical representation of the pairs (1-specificity, sensitivity). is the area formed by the ROC curve, which equals to 1 in an ideal test. The comparison of the possible combinations for each stage of the study revealed the following results. In the analyses without feature selection, the best results were (1) 100% accuracy and of 0.99 for the combination of PT, LBP and internal masks and (2) 99.5% accuracy and of 0.99 for the combination of GA, LBP and internal masks for the extraction of features. In the analyses with feature selection, the best results were (1) 100% accuracy and of 1.0 for the combination of GA and LBP (feature extraction) with the union of internal and external masks and (2) 98.5% accuracy and of 0.99 for the combination of PT, LBP and the union of internal and external masks.

EFFICIENT TEXTURE BASED FUZZY DISTANCE CLUSTERING AND SOM OPTIMAL CLASSIFIER FOR FOREGROUND MOVING OBJECT DETECTION

Ponte Academic JournalNov 2017, Volume 73, Issue 11 EFFICIENT TEXTURE BASED FUZZY DISTANCE CLUSTERING AND SOM OPTIMAL CLASSIFIER FOR FOREGROUND MOVING OBJECT DETECTIONAuthor(s): V. Naga Bushan ,Ch. Satyananda ReddyJ. Ponte - Nov 2017 - Volume 73 - Issue 11 doi: 10.21506/j.ponte.2017.11.10 Abstract:Foreground moving object detection plays a critical role in video surveillance systems. Local Binary Pattern (LBP) based fuzzy distance segmentation is proposed for object foreground detection which uses modified training rate that deals with a change in the foreground of different rates. The extracted features are trained by using hybrid self-organizing map (SOM) based artificial bee colony (ABC) optimization. This approach deals with dynamic background and the illumination changes effectively. In this fuzzy c_means based segmentation effectively segments the moving object for foreground detection. Then, the feature from the foreground is extracted using the LBP feature extraction technique. Thus, foreground image can be further classified for identifying the object under moving using SOM with optimization. The proposed work is simulated in the working platform of Matlab, and the performance is analyzed by comparing with the existing techniques. Experimental results declare that the proposed method accomplishes more changes in the precision over existing techniques. Download full text:Check if you have access through your login credentials or your institution Username Password

A novel mobile robot localization approach based on topological maps using classification with reject option in omnidirectional images

Mobile robot localization, which allows a robot to identify its position, is one of main challenges in the field of Robotics. In this work, we provide an evaluation of consolidated feature extractions and machine learning techniques from omnidirectional images focusing on topological map and localization tasks. The main contributions of this work are a novel method for localization via classification with reject option using omnidirectional images, as well as two novel omnidirectional image data sets. The localization system was analyzed in both virtual and real environments. Based on the experiments performed, the Minimal Learning Machine with Nearest Neighbors classifier and Local Binary Patterns feature extraction proved to be the best combination for mobile robot localization with accuracy of 96.7% and an Fscore of 96.6%.

Epileptic seizure detection in long-term EEG records using sparse rational decomposition and local Gabor binary patterns feature extraction

In this paper, we address the problem of off-line supervised detection of epileptic seizures in long-term Electroencephalography (EEG) records. A novel feature extraction method is proposed based on the sparse rational decomposition and the Local Gabor Binary Patterns (LGBP). Namely, we decompose the channels of the EEG record into 8 sparse rational components using a group of optimal coefficients. Then, a modified 1D LGBP operator is applied, which is followed by downsampling of the data. The width of the largest LGBPs is finally computed for all the 8 rational components and the 23 channels of the EEG record. Hence, we characterize seizure patterns of one-second-long EEG epochs by 23 × 8 features. The effectiveness of the proposed feature extraction method is assessed using different classifiers which are trained with 25% of early EEG records of each patient. We performed an extensive comparative study over 163 h of EEG recordings from the CHB-MIT Scalp EEG database. The experiments show that the proposed technique outperforms other dedicated techniques by achieving the overall sensitivity of 70.4% and the overall specificity of 99.1%, in the patient-specific detection of epileptic EEG epochs. Moreover, it detects onset of seizures with the overall sensitivity of 91.13% and false alarms per hour rate of 0.35, on average.

DME Detection using LBP Features

A system for detecting Diabetic Macular Edema (DME) using Optical Coherence Tomography (OCT) volumes is presented. In preprocessing stage noise removal and flattening of scans is done which is followed by Local binary pattern feature extraction. The extracted features are then classified using linear support vector machine classifier. The proposed system achieved an specificity and sensitivity of 100% and 86.67% respectively. General Terms Pattern Recognition, Digital Image Processing, Computer Vision

A cloud-based monitoring system via face recognition using Gabor and CS-LBP features

Face detection and recognition is an important topic in security. Currently, ubiquitous monitoring has received a large amount of attention. This paper proposes a cloud-based ubiquitous monitoring system via face recognition. It consists of a monitoring client module for face detection and recognition and a cloud storage module for data visualization. In the monitoring client module, the center-symmetric local Gabor binary pattern feature extraction method is proposed for face recognition, which combines improved multi-scale Gabor and center-symmetric local binary pattern (CS-LBP) features. This method maintains crucial local features, reduces the Gabor filter complexity, and adds rotational invariance and more precise texture information. A large number of experiments on the ORL, Yale-B, and Yale databases show that the proposed method obtains significantly better recognition rates than the LBP, CS-LBP, and Scale Gabor methods. Furthermore, we propose a Web browser-based data visualization that renders the geographic locations of the face detection and recognition results.

Classification of Textures Using Filter Based Local Feature Extraction

In this work local features are used in feature extraction process in image processing for textures. The local binary pattern feature extraction method from textures are introduced. Filtering is also used during the feature extraction process for getting discriminative features. To show the effectiveness of the algorithm before the extraction process, three different noise are added to both train and test images. Wiener filter and median filter are used to remove the noise from images. We evaluate the performance of the method with Naive Bayesian classifier. We conduct the comparative analysis on benchmark dataset with different filtering and size. Our experiments demonstrate that feature extraction process combine with filtering give promising results on noisy images.

基于自适应提升小波变换和LBP的极光分类算法

本文提出了一种新的基于自适应提升小波变换的双尺度算法、改进的局部二值模式和模糊近邻分类相结合的极光分类算法。该算法在极光图像预处理的基础之上，先是利用自适应提升的小波变换将原始的极光图像分为几个子图像，然后再对各个子图像进行变尺度的高斯滤波。用局部二值模式进行对子图像进行特征的提取，最后用模糊的近邻分类算法对其进行分类。仿真实验证明，首先本文算法的分类效率高于其他极光分类算法，其次就是本文算法对普通的噪声，例如高斯噪声和椒盐噪声，都有较好的鲁棒性。 This paper presents a new dual-scaling algorithm based on adaptive lifting wavelet transform and improved Local Binary Pattern and classification of a combination of fuzzy neighbor Aurora classi-fication algorithm. Based on the aurora image preprocessing, the algorithm is first using adaptive lifting wavelet transform of the original image to divide into several sub-images of Aurora, and then for each sub-image variable scale Gaussian filter, and to conduct sub-picture with the local binary pattern feature extraction, and finally with fuzzy neighbor classification algorithm to classify. Simulation results show that, first, the algorithm classification efficiency is higher than other Aurora classification algorithm, followed by the algorithm for ordinary noise, such as Gaussian noise and salt and pepper noise having better robustness.

Semi-Local Structure Patterns for Robust Face Detection

In many image processing and computer vision problems, including face detection, local structure patterns such as local binary patterns (LBP) and modified census transform (MCT) have been adopted in widespread applications due to their robustness against illumination changes. However, being reliant on the local differences between neighboring pixels, they are inevitably sensitive to noise. To overcome the problem of noise-vulnerability of the conventional local structure patterns, we propose semi-local structure patterns (SLSP), a novel feature extraction method based on local region-based differences. The SLSP is robust to illumination variations, distortion, and sparse noise because it encodes the relative sizes of the central region with locally neighboring regions into a binary code. The principle of SLSP leads noise-robust expansions of LBP and MCT feature extraction frameworks. In a statistical analysis, we find that the proposed methods transform a substantial amount of random noise patterns in face images into more meaningful uniform patterns. The empirical results on the ${\rm MIT} + {\rm CMU}$ dataset and FDDB (face detection dataset and benchmark) show that the proposed semi-local patterns applied to LBP and MCT feature extraction frameworks outperform the conventional LBP and MCT features in AdaBoost-based face detectors, with much higher detection rates.

Multiresolution local binary pattern variants based texture feature extraction techniques for efficient classification of microscopic images of hardwood species

In this paper, multiresolution local binary pattern (MRLBP) variants based texture feature extraction techniques have been proposed to categorize hardwood species into its various classes. Initially, discrete wavelet transform (DWT) has been used to decompose each image up to 7 levels using Daubechies wavelet (db2) as decomposition filter. Subsequently, six texture feature extraction techniques (local binary pattern and its variants) are employed to obtain substantial features of these images at different levels. Three classifiers, namely, linear discriminant analysis (LDA), linear and radial basis function (RBF) kernel support vector machine (SVM), have been used to classify the images of hardwood species. Thereafter, classification results obtained from conventional and MRLBP variants based texture feature extraction techniques with different classifiers have been compared. For 10-fold cross validation approach, texture features acquired using discrete wavelet transform based uniform completed local binary pattern (DWTCLBPu2) feature extraction technique has produced best classification accuracy of 97.40±1.06% with linear SVM classifier. This classification accuracy has been achieved at the 3rd level of image decomposition using full feature (1416) dataset. Further, reduction in dimension of texture features (325 features) by principal component analysis (PCA) has been done and the best classification accuracy of 97.87±0.82% for DWTCLBPu2 at the 3rd level of image decomposition has been obtained using LDA classifier. The DWTCLBPu2 texture features have also established superiority among the MRLBP techniques with reduced dimension features for randomly divided database into fix training and testing ratios.

Intelligent drowsy eye detection using image mining

Cell phones, MP4 players, and GPS all distract drivers, forcing them to divide their attention to what is happening outside and what is happening inside the vehicle. Preventing drivers from falling asleep at the wheel and drifting off on the road is an increasingly hard task but a solution can be achieved with today's technology: by capturing driver's eye gaze and thus the level of their exhaustion, the potential for safer roads is real. Today, image mining systems can automatically extract important information from an image dataset which can then be used to classify images and image relationship that been applied in different areas. The basic challenge in image mining research area is to determine how image level pixel representation in an original image can be used and constructed to then identify meaningful information or form relationships. In this research Intelligent Drowsy Eye Detection, using an Image Mining (IDEDIM) system is proposed. The proposed architecture would use different feature extraction techniques and three data mining classification techniques to aid with accurate information collection. Two thousand left and right eye images were used to test the developed system by Discrete Wavelet Transform (DWT), Statistical features, and Local binary pattern (LBP) feature extraction techniques. The extracted features were used as input for Decisions Tree C5.0, K Nearest Neighbor (KNN), and the Support Vector Machine (SVM) Classifier. After several experimental sets, the C5.0 and KNN classifier were performing better than SVM classifier. Based on the results, we recommend the inclusion of LBP and DWT in conjunction with C5.0 with KNN as a classification technique. To validate the achieved results, Receiver Operating Characteristic (ROC) curve is used to compare among the proposed classifiers. The proposed system can be integrated with the existing subsystem into real time Drowsy Detection System to achieve excellent accuracy and performance.

Integrated multilevel image fusion and match score fusion of visible and infrared face images for robust face recognition

This paper presents an integrated image fusion and match score fusion of multispectral face images. The fusion of visible and long wave infrared face images is performed using 2 ν -granular SVM which uses multiple SVMs to learn both the local and global properties of the multispectral face images at different granularity levels and resolution. The 2 ν -GSVM performs accurate classification which is subsequently used to dynamically compute the weights of visible and infrared images for generating a fused face image. 2D log polar Gabor transform and local binary pattern feature extraction algorithms are applied to the fused face image to extract global and local facial features, respectively. The corresponding match scores are fused using Dezert Smarandache theory of fusion which is based on plausible and paradoxical reasoning. The efficacy of the proposed algorithm is validated using the Notre Dame and Equinox databases and is compared with existing statistical, learning, and evidence theory based fusion algorithms.