Face recognition using statistical adapted local binary patterns.

One of the most representative manners which human shows his inner feelings is through facial expressions. Automatic recognition of these gestures is of great importance in human computer interaction (HCI) applications. In order to automatically recognize facial expressions, local binary patterns (LBPs), which are powerful and computationally simple descriptors, have been extensively utilized for feature extraction from facial images. To improve image description accuracy, we have employed a new version of LBP, namely high order joint derivative local binary pattern (HJDLBP) in this paper which reveals spatial relations between patterns in different resolutions. Furthermore, a rotation invariant radial partitioning paradigm is utilized to localize LBP histogram calculation regions. Using radial partitioning instead of blocking eliminates head rotation effects in real world applications and improves classification accuracy. A bunch of support vector machines are trained by feature vectors to classify different facial expressions. To evaluate the proposed method we have used known and publicly available JAFFE dataset for experiments and compared the obtained results with results from state of the art approaches which use original LBP and rectangular partitioning. The comparison results show the effectiveness of the new descriptor in combination with radial partitioning for automatic facial expression categorization.

This paper proposes a novel approach in image compression based on Local Binary Pattern (LBP). LBP has already been used as a simple texture descriptor, labeling the image pixels by looking at the points surrounding a central point (usually on a 3×3 neighborhood) and examining whether these neighbors' color values are greater or less than the central point and accordingly assigning a binary value to the corresponding bit. The description of image's local pattern results in an eight-bit binary description, but in order to restore the image from such a LBP description, the value of each central pixel is also needed. These two pieces of information, i.e. the LBP description and the actual original value for each local neighborhood central pixel, are stored in a newly proposed Local Binary Compressed format, denoted .LBC, from which the image can be reconstructed by employing statistical methods, i.e. generating smaller or larger sets of random numbers to fill in the missing information within each local neighborhood, based on the LBP descriptor. Two statistical distributions were tested and, apart from the compression performance, a Structural Similarity Index Metric was used to evaluate the results.

Recently, there has been a huge demand for assistive technology for industrial, commercial, automobile, and societal applications. In some of these applications, there is a requirement of an efficient and accurate system for automatic facial expression recognition (FER). Therefore, FER has gained enormous interest among computer vision researchers. Although there has been a plethora of work available in the literature, an automatic FER system has not yet reached the desired level of robustness and performance. In most of these works, there has been the dominance of appearance-based methods primarily consisting of local binary pattern (LBP), local directional pattern (LDP), local ternary pattern (LTP), gradient local ternary pattern (GLTP), and improved local ternary pattern (IGLTP). Keeping in view the popularity of appearance-based methods, in this paper, we have proposed an appearance-based descriptor called Improved Adaptive Local Ternary Pattern (IALTP) for automatic FER. This new descriptor is an improved version of ALTP, which has been proved to be effective in face recognition. We have investigated ALTP in more details and have proposed some improvements like the use of uniform patterns and dimensionality reduction via principal component analysis (PCA). The reduced features are then classified using kernel extreme learning machine (K-ELM) classifier. In order to validate the performance of the proposed method, experiments have been conducted on three different FER datasets using well-known evaluation measures such as accuracy, precision, recall, and F1-Score. The proposed approach has also been compared with some of the state-of-the-art works in literature and found to be more accurate and efficient.

LSCO: Light spectrum chimp optimization based spinalnet for live face detection and recognition

PLBP: An effective local binary patterns texture descriptor with pyramid representation

The Local Binary Patterns (LBP) feature extraction method is a theoretically and computationally simple and efficient methodology for texture analysis. The LBP operator is used in many applications such as facial expression recognition and face recognition. The original LBP is based on hard thresholding the neighborhood of each pixel, which makes texture representation sensitive to noise. In addition, LBP cannot distinguish between a strong and a weak pattern. In order to enhance the LBP approach, Fuzzy Local Binary Patterns (FLBP) is proposed. In FLBP, any neighborhood does not represented only by one code, but, it is represented by all existing codes with different degrees. In FLBP, any fuzzy Intersection and Union operators may be used. In this study, the following operators are applied and their results are compared together: Dot-Sum, Min-Max and normalized Min-Max. Based on the extensive experiments, the fuzzy Min-Max operators are more useful and can improve the accuracy in the application of Facial Expression Recognition (FER) about 4% (i.e., form 82.98% to 86.88%).

The local binary pattern (LBP) and its variants have shown the effectiveness in texture images classification, face recognition, and other applications. However, most of these LBP methods only focus on the histogram of LBP patterns and ignore the spatial contextual information between LBP patterns. In this paper, we propose a 2D-LBP method which uses a sliding window to count the weighted occurrence number of the rotation invariant uniform LBP pattern pairs to obtain the spatial contextual information. The multi-resolution 2D-LBP features can also be obtained when the radius of 2D-LBP is changed. At last, a two-stage classifier which acts as an ensemble learning step is followed to achieve an accurate classification by combining the predictions on each 2D-LBP with single resolution. Theoretical proof shows that the proposed 2D-LBP is a general framework and can be integrated on other LBP variants to derive new feature extraction methods. Experimental results show that, the proposed method achieves 99.71%, 97.09%, 98.48%, and 49.00% classification accuracy on the public “Brodatz,” “CUReT,” “UIUC,” and “FMD” texture image databases, respectively. Compared with the original LBP and its variants, the proposed method obtains higher classification accuracy under different cases, and simultaneously owns shorter time complexity.

In this paper, we describe a novel local descriptor of image texture representation for visual recognition. The image features based on micro-descriptors such as local binary patterns (LBP) and local ternary patterns (LTP) have been very successful in a number of applications including face recognition, object detection, and texture analysis. Instead of binary quantization in LBP, LTP thresholds the differential values between a focused pixel and its neighborhood pixels into three gray levels, which can be explained as the active status (i.e., positively activated, negatively activated, and not activated) of the neighborhood pixels compared to the focused pixel. However, regardless of the magnitude of the focused pixel, the thresholding strategy remains fixed, which would violate the principle of human perception. Therefore, in this study, we design LTP with a data-driven threshold according to Weber’s law, a human perception principle; further, our approach incorporates the contexts of spatial and orientation co-occurrences (i.e., co-occurrence context) among adjacent Weber-based local ternary patterns (WLTPs, i.e., data-driven quantized LTPs) for texture representation. The explored WLTP is formulated by adaptively quantizing differential values between neighborhood pixels and the focused pixel as negative or positive stimuli if the normalized differential values are large; otherwise, the stimulus is set to 0. Our approach here is based on the fact that human perception of a distinguished pattern depends not only on the absolute intensity of the stimulus but also on the relative variance of the stimulus. By integrating co-occurrence context information, we further propose a rotation invariant co-occurrence WLTP (RICWLTP) approach to be more discriminant for image representation. In order to validate the efficiency of our proposed strategy, we apply this to three different visual recognition applications including two texture datasets and one food image dataset and prove the promising performance that can be achieved compared with the state-of-the-art approaches.

Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples). Therefore, a presentation attack detection (PAD) method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP), local ternary pattern (LTP), and histogram of oriented gradients (HOG). As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN) method to extract deep image features and the multi-level local binary pattern (MLBP) method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM) method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases.

Texture is the surface property that is used to identify and recognise objects. This property is widely used in many applications including texture-based face recognition systems, surveillance, identity verification and so on. The Local binary pattern (LBP) texture method is most successful for face recognition. Owing to the great success of LBP, recently many models, which are variants of LBP have been proposed for texture analysis. Some of the derivatives of LBPs are multivariate local binary pattern, centre symmetric local binary pattern, local binary pattern variance, dominant local binary pattern, advanced local binary pattern, local texture pattern (LTP) and local derivative pattern (LDP). In this scenario, it is essential to review, whether LBP or their derivatives perform better for face recognition. The real-time challenges such as illumination changes, rotations, angle variations and facial expression variations are evaluated by different LBP-based models. Experiments were conducted on the Japanese female facial expression, YALE and FRGC version2 databases. The results show that LDP and LTP perform much better than the other LBP-based models.

Face classification is a technique used in Biometrics to help distinguish between facial images. However, this technique has been applicable on human face images only. Online virtual worlds such as Second Life, Sims Online, etc. are gaining popularity over the Internet. They require human users to create a digital persona of oneself, known as an "avatar". Several avatars are designed to resemble human users. With crime being reported in virtual worlds, computer-generated avatar faces being created from human faces and human-resembling humanoids being designed, there is a need to distinguish between natural and artificial faces. Our work applies two new face classification techniques on grayscale, facial images of humans and avatars to tell them apart. (1) Uniform Local Directional Pattern (ULDP) utilizes the uniform patterns from Local Directional Pattern (LDP) (2) Wavelet Uniform Local Directional Pattern (WULDP) applies the ULDP technique on the wavelet transform of an image. Extensive experiments conducted on five different face image datasets (Caltech, FERET for human faces and Entropia, Second Life, Evolver for avatar faces) achieve baseline average classification accuracies of 98.55% using ULDP and 89.55% using WULDP respectively.

Gender identification is a new domain in image recognition. Gender identification of human face is to judge one's gender according to his/her face features. The article adopted local binary pattern (LBP) algorithm to build feature subspaces, and processed data using Support Vector Machine (SVM) learning models. Experiments showed that integration of LBP algorithm with linear SVM and integration of LBP algorithm with low-order polynomial SVM are better than Gauss-kernel function.

Breast density is considered to be one of the major risk factors in developing breast cancer. High breast density can also affect the accuracy of mammographic abnormality detection due to the breast tissue characteristics and patterns. We reviewed variants of local binary pattern descriptors to classify breast tissue which are widely used as texture descriptors for local feature extraction. In our study, we compared the classification results for the variants of local binary patterns such as classic LBP (Local Binary Pattern), ELBP (Elliptical Local Binary Pattern), Uniform ELBP, LDP (Local Directional Pattern) and M-ELBP (Mean-ELBP). A wider comparison with alternative texture analysis techniques was studied to investigate the potential of LBP variants in density classification. In addition, we investigated the effect on classification when using descriptors for the fibroglandular disk region and the whole breast region. We also studied the effect of the Region-of-Interest (ROI) size and location, the descriptor size, and the choice of classifier. The classification results were evaluated based on the MIAS database using a ten-run ten-fold cross validation approach. The experimental results showed that the Elliptical Local Binary Pattern descriptors and Local Directional Patterns extracted most relevant features for mammographic tissue classification indicating the relevance of directional filters. Similarly, the study showed that classification of features from ROIs of the fibroglandular disk region performed better than classification based on the whole breast region.

Local binary pattern (LBP) is sensitive to noise. Local ternary pattern (LTP) partially solves this problem. Both LBP and LTP, however, treat the corrupted image patterns as they are. In view of this, we propose a noise-resistant LBP (NRLBP) to preserve the image local structures in presence of noise. The small pixel difference is vulnerable to noise. Thus, we encode it as an uncertain state first, and then determine its value based on the other bits of the LBP code. It is widely accepted that most of the image local structures are represented by uniform codes and noise patterns most likely fall into the non-uniform codes. Therefore, we assign the value of an uncertain bit hence as to form possible uniform codes. Thus, we develop an error-correction mechanism to recover the distorted image patterns. In addition, we find that some image patterns such as lines are not captured in uniform codes. Those line patterns may appear less frequently than uniform codes, but they represent a set of important local primitives for pattern recognition. Thus, we propose an extended noise-resistant LBP (ENRLBP) to capture line patterns. The proposed NRLBP and ENRLBP are more resistant to noise compared with LBP, LTP, and many other variants. On various applications, the proposed NRLBP and ENRLBP demonstrate superior performance to LBP/LTP variants.

Face recognition is an area of computer vision that has attracted a lot of interest from the research community. A growing demand for robust face recognition software in security applications has driven the development of interesting approaches in this field. A large quantity of research in face recognition deals with visible face images. In the visible spectrum the illumination and face expressions changes represent a significant challenge for the recognition system. To avoid these problems, researchers proposed recently the use of 3D and infrared imaging for face recognition. In this work, we introduce a new framework for infrared face recognition using texture descriptors. This framework exploits linear and non linear dimensionality reduction techniques for face learning and recognition in the texture space. Active and passive infrared imaging modalities are used and comparison with visible face recognition is performed. Two multispectral face recognition databases were used in our experiments: Equinox Database (Visible, SWIR, MWIR, LWIR) and Laval University Multispectral Database (Visible, NIR, MWIR, LWIR). The obtained results show high increase in recognition performance when texture descriptors like LBP (Local Binary Pattern) and LTP (Local Ternary Pattern) are used. The best result was obtained in the short wave infrared spectrum (SWIR) using non linear dimensionality reduction techniques.