Moving Vehicle Detection in Traffic Video Using Modified SXCS-LBP Texture Descriptor

In this chapter, the authors proposed background modeling and subtraction-based methods for moving vehicle detection in traffic video using a novel texture descriptor called Modified Spatially eXtended Center Symmetric Local Binary Pattern (Modified SXCS-LBP) descriptor. The XCS-LBP texture descriptor is sensitive to noise because in order to generate binary code, the value of center pixel value is used as the threshold directly, and it does not consider temporal motion information. In order to solve this problem, this chapter proposed a novel texture descriptor called Modified SXCS-LBP descriptor for moving vehicle detection based on background modeling and subtraction. The proposed descriptor is robust against noise, illumination variation, and able to detect slow moving vehicles because it considers both spatial and temporal moving information. The evaluation is carried out using precision and recall metric, which is obtained using experiments conducted on popular dataset such as BMC dataset. The experimental result shows that the method outperforms existing methods.

Spoofing Face Detection using LBP Descriptor and KNN Classifier in Image Processing

Image processing in today’s world used for performing operations on images by using a process of making positive suggestion of face which can be in a photo or video in already existing face database. Extraction of face attributes is done in face detection from photos and also from videos. When any unauthorized person tries to enter in authentication system by presenting fraud image and video is termed as spoofing attack. Biometrics is a technology which recognizes characteristics of human and is prone to spoof attacks. The detection of spoofed faces by recognizing and exploring the fake face and genuine face images is called face spoof detection. The DWT method is used to inspect the textual attribute occurring within the test images. There is a possibility that some unusual disruptions are available like geometric disruption and the artificial texture disruption. Eigen face technique is applicable for taking out attributes. Histogram for every feature or attributes is determined and employed a collation of essence to find out face spoof detection. To explore even if the image is actual and gag, already used approach Support Vector Machine is used. To make face spoof detection more accurate KNN classifier will take the place of the SVM classifier. The Contrast are construct to inspect the performance of the suggest algorithm and the existing algorithm in two parameters accuracy and time of execution. Detection of spoofed faces can be used for security purpose, preventing crime, access control system.

A Novel Approach to Improve Face Recognition Process Using Automatic Learning

In real-life applications, the appearance of a face changes significantly due to variations in expression, lighting, aging, exposure, and occlusion, which makes face recognition difficult. We present in this article a new approach for facial recognition. This approach is based on a set of variants of the Ho-LBP descriptor that we have proposed. In fact, the presentation of the images using a set of variants of the Ho-LBP descriptor helps the classifier to learn better. In addition, these variants are combined to improve the performance of facial recognition. We evaluated the effectiveness of our approach on ORL, Extended Yale B, and Feret databases. The obtained results are very promising, especially when compared with those of existing approaches. They show that our approach improves the accuracy of facial recognition in a very efficient way and in particular to the variations of the poses and the changes of the luminance.

Face Spoofing Detection using Enhanced Local Binary Pattern

Among various biometric systems, over the past few years identifying the face patterns has become the centre of attraction, owing to this, a substantial improvement has been made in this area. However, the security of such systems may be a crucial issue since it is proved in many studies that face identification systems are susceptible to various attacks, out of which spoofing attacks are one of them. Spoofing is defined as the capability of making fool of a system that is biometric for finding out the unauthorised customers as an actual one by the various ways of representing version of synthetic forged of the original biometric trait to the sensing objects. In order to guard face spoofing, several anti-spoofing methods are developed to do liveliness detection. Various techniquesfordetection of spoofing make the use of LBP i.e. local binary patterns that make the difference to symbolise handcrafted texture features from images, whereas, recent researches have shown that deep features are more robust in comparison to the former one. In this paper, a proper countermeasure in opposite to attacks that are on face spoofing are relied on CNN i.e. Convolutional Neural Network. In this novel approach, deep texture features from images are extracted by integrating the modified version of LBP descriptor (Gene LBP net) to a CNN. Experimental results are obtained on NUAA spoofing database which defines that these deep neural network surpass most of the state-of-the-art techniques, showing good outcomes in context to finding out the criminal attacks

Robust Ship Tracking via Multi-view Learning and Sparse Representation

Conventional visual ship tracking methods employ single and shallow features for the ship tracking task, which may fail when a ship presents a different appearance and shape in maritime surveillance videos. To overcome this difficulty, we propose to employ a multi-view learning algorithm to extract a highly coupled and robust ship descriptor from multiple distinct ship feature sets. First, we explore multiple distinct ship feature sets consisting of a Laplacian-of-Gaussian (LoG) descriptor, a Local Binary Patterns (LBP) descriptor, a Gabor filter, a Histogram of Oriented Gradients (HOG) descriptor and a Canny descriptor, which present geometry structure, texture and contour information, and more. Then, we propose a framework for integrating a multi-view learning algorithm and a sparse representation method to track ships efficiently and effectively. Finally, our framework is evaluated in four typical maritime surveillance scenarios. The experimental results show that the proposed framework outperforms the conventional and typical ship tracking methods.

Face recognition based on stable uniform patterns

Face recognition (FR) is one of the challenging and active research fields of image processing, computer vision and biometrics with numerous proposed systems. We present a feature extraction method named “stable uniform local pattern (SULP)”, a refined variant of ULBP operator, for robust face recognition. The SULP directly applied on gradient face images (in x and y directions) of a single image for capturing significant fundamental local texture patterns to build up a feature vector of a face image. Histogram sequences of SULP images of the two gradient images are finally concatenated to form the “stable uniform local pattern gradient (SULPG)” vector for the given image. The SULPG approach is experimented on Yale, ATT-ORL, FERET, CAS-PEAL and LFW face databases and the results are compared with the LBP model and various variants of LBP descriptor. The results indicate that the present descriptor is more powerful against a wide range of challenges, such as illumination, expression and pose variations and outperforms the state-of-the-art methods based on LBP.