Center-symmetric Local Binary Pattern Research Articles

A texture descriptor: BackGround Local Binary Pattern (BGLBP)

Local Binary Pattern (LBP) is invariant to the monotonic changes in the grey scale domain. This property enables LBP to present a texture descriptor being useful in applications dealing with the local illumination changes. However, the existing versions of LBP are not able to handle image illumination changes, especially in outdoor environments. The non-patterned illumination changes disturb performance of the background extraction methods. In this paper, an extended version of LBP which is called BackGround LBP (BGLBP) is presented. BGLBP is designed for the background extraction application but it is extendable to the other areas as a texture descriptor. BGLBP is an extension of D-LBP, Centre-Symmetric LBP, ULBP, and R-LBP and it has been designed to inherit the positive properties of previous versions. The performance of BGLBP as a part of background extraction method is investigated. In addition, a comparison between BGLBP as a general texture descriptor and a number of LBP versions is conducted.

Perceptual image hashing using center-symmetric local binary patterns

Perceptual image hashing finds increasing attention in several multimedia security applications such as image identification/authentication, tamper detection, and watermarking. Robust feature extra...

Sparse Hierarchical Clustering for VHR Image Change Detection

The traditional clustering approaches are limited for the unsupervised change detection of very high resolution images due to the multimodal distribution of change features. To overcome this difficulty, a sparse hierarchical clustering approach is proposed. Discriminative change features are generated by stacking bitemporal multiscale center-symmetric local binary pattern features. In order to explore the multimodal and hierarchical distribution of the change features, a tree-structured dictionary is learned from the pseudotraining set and the unlabeled data. The sparse reconstruction error, a more robust distance compared to the Euclidean distance, is used to determine the label of each change feature. Comparative experiments demonstrate the effectiveness of the proposed method.

Variable-length signature for near-duplicate image matching.

We propose a variable-length signature for near-duplicate image matching in this paper. An image is represented by a signature, the length of which varies with respect to the number of patches in the image. A new visual descriptor, viz., probabilistic center-symmetric local binary pattern, is proposed to characterize the appearance of each image patch. Beyond each individual patch, the spatial relationships among the patches are captured. In order to compute the similarity between two images, we utilize the earth mover's distance which is good at handling variable-length signatures. The proposed image signature is evaluated in two different applications, i.e., near-duplicate document image retrieval and near-duplicate natural image detection. The promising experimental results demonstrate the validity and effectiveness of the proposed variable-length signature.

Directional local ternary patterns for multimedia image indexing and retrieval

In this paper, we proposed a novel multimedia image indexing and retrieval algorithm using Directional Local Ternary Pattern (DLTP) for Content-Based Image Retrieval (CBIR). The standard Local Binary Pattern (LBP) and Local Ternary Pattern (LTP) encode the relationship between reference pixel and its surrounding neighbours by computing grey-level difference. The proposed method extracts the directional edge information based on local ternary value (−1, 0, 1) instead of binary value (0, 1) in 0°, 45°, 90°, and 135° directions of an image. The performance of the proposed method is compared with local binary pattern LBP, Block-based LBP (BLK-LBP), Centre-Symmetric LBP (CS-LBP), Local Edge Patterns for Segmentation (LEPSEG), Local Edge Patterns for Image Retrieval (LEPINV) and other existing transform domain methods based on Corel-5000 (DB1) and Corel-10000 (DB2) databases. The retrieval performance of DLTP shows better improvement in terms of their performance measures as compared with the standard LBP.

OBJECT RECOGNITION BASED ON BAG OF FEATURES AND A NEW LOCAL PATTERN DESCRIPTOR

Bag of Features (BoF) has gained a lot of interest in computer vision. Visual codebook based on robust appearance descriptors extracted from local image patches is an effective means of texture analysis and scene classification. This paper presents a new method for local feature description based on gray-level difference mapping called Mean Local Mapped Pattern (M-LMP). The proposed descriptor is robust to image scaling, rotation, illumination and partial viewpoint changes. The training set is composed of rotated and scaled images, with changes in illumination and view points. The test set is composed of rotated and scaled images. The proposed descriptor more effectively captures smaller differences of the image pixels than similar ones. In our experiments, we implemented an object recognition system based on the M-LMP and compared our results to the Center-Symmetric Local Binary Pattern (CS-LBP) and the Scale-Invariant Feature Transform (SIFT). The results for object classification were analyzed in a BoF methodology and show that our descriptor performs better compared to these two previously published methods.

Parallax Effect Free Mosaicing of Underwater Video Sequence Based on Texture Features

In this paper, we present feature-based technique for construction of mosaic image from underwater video sequence, which suffers from parallax distortion due to propagation properties of light in the underwater environment. The most of the available mosaic tools and underwater image mosaicing techniques yields final result with some artifacts such as blurring, ghosting and seam due to presence of parallax in the input images. The removal of parallax from input images may not reduce its effects instead it must be corrected in successive steps of mosaicing. Thus, our approach minimizes the parallax effects by adopting an efficient local alignment technique after global registration. We extract texture features using Centre Symmetric Local Binary Pattern (CS-LBP) descriptor in order to find feature correspondences, which are used further for estimation of homography through RANSAC. In order to increase the accuracy of global registration, we perform preprocessing such as colour alignment between two selected frames based on colour distribution adjustment. Because of existence of 100% overlap in consecutive frames of underwater video, we select frames with minimum overlap based on mutual offset in order to reduce the computation cost during mosaicing. Our approach minimizes the parallax effects considerably in final mosaic constructed using our own underwater video sequences.

Facial expression recognition based on two-stage features extraction

Facial expression recognition plays an important role in a variety of real-world applications such as human–computer interaction, robot control, smart meeting, and visual surveillance. One critical step for facial expression recognition is to accurately extract emotional features. In this article, a facial expression recognition approach based on two-stage local facial textures extraction is proposed. At the first stage, we use the threshold local binary pattern to transform a facial image into a feature image. We then extract the most discriminate features from the feature image by using the block-based center-symmetric local binary pattern. Finally, these features are classified by the support vector machine. Experimental results are provided to illustrate the proposed approach is an effective method, compared to other similar methods.

HSOG: a novel local image descriptor based on histograms of the second-order gradients.

Recent investigations on human vision discover that the retinal image is a landscape or a geometric surface, consisting of features such as ridges and summits. However, most of existing popular local image descriptors in the literature, e.g., scale invariant feature transform (SIFT), histogram of oriented gradient (HOG), DAISY, local binary Patterns (LBP), and gradient location and orientation histogram, only employ the first-order gradient information related to the slope and the elasticity, i.e., length, area, and so on of a surface, and thereby partially characterize the geometric properties of a landscape. In this paper, we introduce a novel and powerful local image descriptor that extracts the histograms of second-order gradients (HSOGs) to capture the curvature related geometric properties of the neural landscape, i.e., cliffs, ridges, summits, valleys, basins, and so on. We conduct comprehensive experiments on three different applications, including the problem of local image matching, visual object categorization, and scene classification. The experimental results clearly evidence the discriminative power of HSOG as compared with its first-order gradient-based counterparts, e.g., SIFT, HOG, DAISY, and center-symmetric LBP, and the complementarity in terms of image representation, demonstrating the effectiveness of the proposed local descriptor.

Face Recognition Based on Weighted Local Binary Pattern with Adaptive Threshold

A new method called weighted Local Binary Pattern (LBP) with adaptive threshold is proposed in this paper to address the shortcomings of LBP and Center Symmetric Local Binary Pattern (CS-LBP), using unflexible threshold and non- discriminating respective sub-patches based on different textures. Firstly, the image is divided into several sub-images and LBP or CS-LBP texture histograms are extracted respectively from each sub-image based on the adaptive threshold. Then, the proposed algorithm adaptively weighted the LBP or CS-LBP histograms of sub-patches with information entropy as their basis and connected all histograms serially to create a final texture descriptor. Finally, the improved efficiency of the proposed algorithm is achieved by speeding up the computation of the average of an image. The experimental results by face databases show that a higher recognition accuracy can be obtained by employing the proposed method with nearest neighbor classification.

Color Directional Local Quinary Patterns for Content Based Indexing and Retrieval

AbstractThis paper presents a novel evaluationary approach to extract color-texture features for image retrieval application namely Color Directional Local Quinary Pattern (CDLQP). The proposed descriptor extracts the individual R, G and B channel wise directional edge information between reference pixel and its surrounding neighborhoods by computing its grey-level difference based on quinary value (−2, −1, 0, 1, 2) instead of binary and ternary value in 0°, 45°, 90°, and 135° directions of an image which are not present in literature (LBP, LTP, CS-LBP, LTrPs, DExPs, etc.). To evaluate the retrieval performance of the proposed descriptor, two experiments have been conducted on Core-5000 and MIT-Color databases respectively. The retrieval performances of the proposed descriptor show a significant improvement as compared with standard local binary pattern LBP, center-symmetric local binary pattern (CS-LBP), Directional binary pattern (DBC) and other existing transform domain techniques in IR system.

Content based image indexing and retrieval using directional local extrema and magnitude patterns

In this paper, we integrate the concept of directional local extremas and their magnitude based patterns for content based image indexing and retrieval. The standard ditectional local extrama pattern (DLEP) extracts the directional edge information based on local extrema in 0°, 45°, 90°, and 135° directions in an image. However, they are not considering the magnitudes of local extremas. The proposed method integrates these two concepts for better retrieval performance. The sign DLEP (SDLEP) operator is a generalized DLEP operator and magnitude DLEP (MDLEP) operator is calculated using magnitudes of local extremas. The performance of the proposed method is compared with DLEP, local binary patterns (LBPs), block-based LBP (BLK_LBP), center-symmetric local binary pattern (CS-LBP), local edge patterns for segmentation (LEPSEG) and local edge patterns for image retrieval (LEPINV) methods by conducting two experiments on benchmark databases, viz. Corel-5K and Corel-10K databases. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to other existing methods on respective databases.

Improving the performance of machine learning algorithms using fuzzy-based features for medical x-ray image classification

This paper proposes a novel approach for medical x-ray image classification using fuzzification of Contourlet-based Center Symmetric Local Binary Patterns (CCS-LBPs). The proposed classification method consists of three stages. In the first stage, local features are obtained by partitioning each image into 25 overlapping sub-images, computing the 2-level contourlet transform of each subimage and extracting CS-LBPs from each resulting subband. In the second stage, fuzzy logic using reduced CCS-LBPs is employed to determine the degree of membership of subimages to each class. Finally, in order to assign images to their respective classes, we utilize membership values as the input of classifiers such as support vector machine (SVM) and k-nearest neighbor (K-NN). This work makes a major contribution to improve the performance of these classifiers. We conducted experiments on a subset of IRMA dataset to evaluate the effectiveness of our classification scheme. Experimental results reveal that the proposed scheme not only achieves a very good performance but also learns well even with a small number of training images.

Human tracking in thermal images using adaptive particle filters with online random forest learning

This paper presents a fast and robust human tracking method to use in a moving long-wave infrared thermal camera under poor illumination with the existence of shadows and cluttered backgrounds. To improve the human tracking performance while minimizing the computation time, this study proposes an online learning of classifiers based on particle filters and combination of a local intensity distribution (LID) with oriented center-symmetric local binary patterns (OCS-LBP). Specifically, we design a real-time random forest (RF), which is the ensemble of decision trees for confidence estimation, and confidences of the RF are converted into a likelihood function of the target state. First, the target model is selected by the user and particles are sampled. Then, RFs are generated using the positive and negative examples with LID and OCS-LBP features by online learning. The learned RF classifiers are used to detect the most likely target position in the subsequent frame in the next stage. Then, the RFs are learned again by means of fast retraining with the tracked object and background appearance in the new frame. The proposed algorithm is successfully applied to various thermal videos as tests and its tracking performance is better than those of other methods.

Center-Symmetric Local Nonsubsampled Contourlet Transform Binary Pattern Histogram Sequence for Face Recognition

In order to alleviate the effect of illumination variations and improve the face recognition rate, this paper proposes a novel non-statistics based face representation method, which is called Center-Symmetric Local Nonsubsampled Contourlet Transform Binary Pattern Histogram Sequence (CS-LNBPHS). This method first applies NSCT to decompose a face image, and obtains NSCT coefficients in different scales and various orientations. Then, CS-LBP operator is used to get CS-LBP feature maps from NSCT coefficients. After that, feature maps are respectively divided into several blocks, the concatenated histogram, which are calculated over each block, are used as the face features. Experimental results on YaleB, ORL face databases show the validity of the proposed approach especially for illumination, face expression and position.

Objects Tracking in Images Sequence Using Center-Symmetric Local Binary Pattern (CS-LBP)

In this paper we present a method for objects tracking in images sequence. This approach is achieved into two main steps. In the first one, we constructed the Center-Symmetric Local Binary Pattern (CS-LBP) histogram pattern of each image in the sequence and the reference pattern. In the second one, we perform the algorithm by the pattern selected based on a distance measures to find similarity between two histograms. The maximum CS-LBP histogram distance gives best results than the chi-square one. The proposed approach has been tested on synthetic and real sequence images and the results are satisfactory.

Scene Classification Algorithm Based on Contextual Semantic Information Extended PLSA Model

In this paper, a novel scene classification algorithm based on contextual visual words combined with extended PLSA model is proposed in which the traditional visual words by contextual information are improved. First, the EICS-LBP (Edge Improved Center Symmetric Local Binary Pattern) and statistical domain color features are extracted from the edge dense sampling region and its 8 neighborhood followed by the computed normalized histogram intersection and the creation of the new feature by linear combination of local information and its contextual intersection information. The visual vocabulary is formed by clustering from dense sampling regions respectively. Then the Bag-Of-Words model is used to describe the image which gives us richer information of scene images and reduces ambiguities and errors. Finally, the potential semantics by extended PLSA model and the confusion table by KNN classifier are obtained. Experiment results show that this method could achieve a higher accuracy, especially performing well in multi-edge color images with contextual information. Besides, it does not require manual annotation on the scene.

Random Forest 분류기와 Bag-of-Feature 특징 히스토그램을 이용한 의료영상 자동 분류 및 검색

This paper presents novel OCS-LBP (Oriented Center Symmetric Local Binary Patterns) based on orientation of pixel gradient and image retrieval system based on BoF (Bag-of-Feature) and random forest classifier. Feature vectors extracted from training data are clustered into code book and each feature is transformed new BoF feature using code book. BoF features are applied to random forest for training and random forest having N classes is constructed by combining several decision trees. For testing, the same OCS-LBP feature is extracted from a query image and BoF is applied to trained random forest classifier. In contrast to conventional retrieval system, query image selects similar K-nearest neighbor (K-NN) classes after random forest is performed. Then, Top K similar images are retrieved from database images that are only labeled K-NN classes. Compared with other retrieval algorithms, the proposed method shows both fast processing time and improved retrieval performance.

Three-level cascade of random forests for rapid human detection

We propose a novel human detection approach that combines three types of center symmetric local binary patterns (CS-LBP) descriptors with a cascade of random forests (RFs). To detect human regions in a low-dimensional feature space, we first extract three types of CS-LBP features from the scanning window of a downsampled saliency texture map and two wavelet-transformed subimages. The extracted CS-LBP descriptors are applied to a three-level cascade of RFs, which combines a series of RF classifiers as a filter chain. The three-level cascade of RFs with CS-LBPs delivers rapid human detection with higher detection accuracy, as compared with combinations of other features and classifiers. The proposed algorithm is successfully applied to various human and nonhuman images from the INRIA dataset, and it performs better than other related algorithms.

가중치 기반 Bag-of-Feature와 앙상블 결정 트리를 이용한 정지 영상에서의 인간 행동 인식

본 논문에서는 CS-LBP (Center-Symmetric Local Binary Pattern) 특징과 공간 피라미드를 이용한 BoF (Bag of Features)를 생성하고 이를 랜덤 포레스트(Random Forest) 분류기에 적용하여 인간의 행동을 인식하는 알고리즘을 제안한다. BoF를 생성하기 위해 영상을 균일한 패치로 나누고, 각 패치 마다 CS-LBP 특징을 추출한다. 행동 분류 성능을 향상시키기 위해 패치들마다 추출한 특징벡터들에 대해 K-mean 클러스터링을 적용하여 코드 북을 생성한다. 본 논문에서는 영상의 지역적인 특성을 고려하기 위해 공간 피라미드 방법을 적용하고 각 공간 레벨에서 추출된 BoF에 대해 가중치를 적용하여 최종적으로 하나의 특징 벡터로 결합한다. 행동 분류를 위해 결정트리의 앙상블로 이루어진 랜덤 포레스트는 학습 단계에서 각 행동 클래스를 위한 분류 모델을 만든다. 가중 BoF가 적용된 랜덤 포레스트는 다양한 인간 행동 영상을 포함하고 있는 Standford Actions 40 데이터를 성공적으로 분류하였다. 또한 기존 방법에 비해 분류 성능이 유사하거나 우수하며, 한 장의 영상에 대해 빠른 인식속도를 보였다. This paper propose a human action recognition method that uses bag-of-features (BoF) based on CS-LBP (center-symmetric local binary pattern) and a spatial pyramid in addition to the random forest classifier. To construct the BoF, an image divided into dense regular grids and extract from each patch. A code word which is a visual vocabulary, is formed by k-means clustering of a random subset of patches. For enhanced action discrimination, local BoF histogram from three subdivided levels of a spatial pyramid is estimated, and a weighted BoF histogram is generated by concatenating the local histograms. For action classification, a random forest, which is an ensemble of decision trees, is built to model the distribution of each action class. The random forest combined with the weighted BoF histogram is successfully applied to Standford Action 40 including various human action images, and its classification performance is better than that of other methods. Furthermore, the proposed method allows action recognition to be performed in near real-time.