Novel face recognition algorithm based on adaptive 3D local binary pattern features and improved Singular Value Decomposition method
01 Aug 2016-pp 1-7
TL;DR: A novel face recognition algorithm based on adaptive 3-D Local Binary Pattern and Singular Value Decomposition method is proposed, which has good feature extraction effect and face recognition performance.
Abstract: Face recognition is a kind of important method focused on biological information identification, which is also a research hotspot in the field of pattern recognition and machine vision. In recent years, some pattern recognition researches show that, human visual system uses a lot of visual-based deep information. Therefore, for face recognition in complex environment, we have research focus on depth images based face recognition system, in order to overcome the problem that the 2-D face recognition system is so sensitive to pose, facial expression and illumination changes. It is remarkable that when we apply statistical method to solve the problems of face depth images recognition, we extremely design feature extraction algorithm for specific training sample set. Nevertheless, once these feature extraction algorithms is completed, there will never be any improvement among them. Thus, this situation leads to the poor universality of the feature extraction algorithms, and the effectiveness and stability of the algorithm will be significantly decreased. As the result, the performance of the recognition system is finally affected. In this paper, we focus on the universality problem of feature extraction algorithm and system identification performance, combining feedback learning theory with Neural Network theory and 3-D Local Binary Pattern feature extraction process. We propose a novel face recognition algorithm based on adaptive 3-D Local Binary Pattern and Singular Value Decomposition method. In the process of face recognition, the most important part is facial feature extraction, by the way, Singular Value Decomposition method regards the face images as a matrix, and obtain image features by segmenting face images. The experimental simulation results show that our algorithm has good feature extraction effect and face recognition performance. We also compare our algorithm with other state-of-the-art methodologies and obtain the better effectiveness.
Citations
More filters
TL;DR: An IoT feature extraction and intrusion detection algorithm for intelligent city based on deep migration learning model, which combines deep learning model with intrusion detection technology is proposed.
130 citations
Journal Article•
TL;DR: A face recognition model is established, and its designed includes image compression, image sampling, input vector standardization, BP neural network and competition selection.
Abstract: The BP neural network is applied in face recognition.A face recognition model is established,and its designed includes image compression,image sampling,input vector standardization,BP neural network and competition selection.The recognition model is simple and has a high recognition rate.
9 citations
20 Apr 2018
TL;DR: A robust face recognition technique is proposed by using local binary pattern and histogram of oriented gradient feature extractor and descriptors by using multiclass support vector machines and it has shown good accuracy rate of recognition.
Abstract: Face recognition, one of the biometric computer vision research area, is a pattern recognition problem which have been done a dozen times since 1960s and it is still a revolutionary area of research interest for many researchers. Although face recognition is the earliest pattern recognition problem yet its accuracy is not as high as other biometric recognition problems like finger print recognition. Different imaging conditions made it challenging like occlusion of faces by hands or eye-glasses, illumination changes, variation in pose and different facial expressions. In this paper we proposed a robust face recognition technique by using local binary pattern and histogram of oriented gradient feature extractor and descriptors. The work has been conducted by carefully acquired and pre-processed 1300 face images, out of it 1040 images were used for training and the rest 260 images for testing purposes. As LBP operators are not good for extracting edge features of a face image we used HOG to extract edge features and LBP for extracting texture features of a face and finally the extracted features has been trained and classified by using multiclass support vector machines and it has shown good accuracy rate of recognition.
6 citations
Cites background from "Novel face recognition algorithm ba..."
...[3] [8] [11] Fig 5 LBP feature calculation example [14]...
[...]
TL;DR: The proposed ubiquitous clouds framework is proposed and the artificial intelligence optimization scheme is applied to the point‐to‐point (P2P) signal transmission network optimization scheme to improve the efficiency of communication network optimization and reduce the optimization cost to a certain extent compared with the state‐of‐the‐art approaches.
2 citations
Cites background from "Novel face recognition algorithm ba..."
...The purpose of artificial intelligence research is to use machines to complete some complex tasks that can only be completed by human natural intelligence.(17) At present, most intelligent network optimization based on artificial intelligence technology relies on the experience of maintenance personnel and some intelligent network optimization tools provided by manufacturers, which is difficult to achieve the systematic, automatic, and continuous intelligent network optimization....
[...]
01 Dec 2020
TL;DR: A neural optimal self-constrained computing model based on fine-tuning island constraints with visual information is presented and the experimental results show that the proposed algorithm has higher processing efficiency and accuracy.
Abstract: With the expansion of the power grid and the acceleration of power information construction, the information communication network covers all aspects and collects accurate information in time to provide continuous and reliable operation for users. The modern power system will gradually enter the era of interconnected power grids. It is more environmentally friendly and efficient than traditional power systems, management is more information and lean, and its operation is safer and more stable. As the infrastructure for carrying smart grid and future energy information interaction, the power communication network has higher and higher requirements for reliability. The coupling between the communication network and the power grid is more and more closely related. The real-time acquisition and the reliable transmission of control information such as the power system require the support of the power communication network. This paper uses machine learning algorithms to learn effective features or patterns from these data and apply them to new data. In this paper, we present a neural optimal self-constrained computing model based on fine-tuning island constraints with visual information. The experimental results show that the proposed algorithm has higher processing efficiency and accuracy.
1 citations
References
More filters
TL;DR: A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
Abstract: We have developed a near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals. The computational approach taken in this system is motivated by both physiology and information theory, as well as by the practical requirements of near-real-time performance and accuracy. Our approach treats the face recognition problem as an intrinsically two-dimensional (2-D) recognition problem rather than requiring recovery of three-dimensional geometry, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as "eigenfaces," because they are the eigenvectors (principal components) of the set of faces; they do not necessarily correspond to features such as eyes, ears, and noses. The projection operation characterizes an individual face by a weighted sum of the eigenface features, and so to recognize a particular face it is necessary only to compare these weights to those of known individuals. Some particular advantages of our approach are that it provides for the ability to learn and later recognize new faces in an unsupervised manner, and that it is easy to implement using a neural network architecture.
14,562 citations
"Novel face recognition algorithm ba..." refers methods in this paper
...Adaptive Feature Extraction Algorithm Adaptive feature extraction algorithm is to combine feedback learning theory with statistical learning process[4], that means we use test samples to implement correction and optimization of the key parameters of algorithms during the process of feature extraction, in order to improve the adaptability of algorithms....
[...]
TL;DR: This work considers the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise, and proposes a general classification algorithm for (image-based) object recognition based on a sparse representation computed by C1-minimization.
Abstract: We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by C1-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.
9,658 citations
"Novel face recognition algorithm ba..." refers methods in this paper
...At the same time, we compare this algorithm with the method proposed in [16]....
[...]
TL;DR: A hybrid neural-network for human face recognition which compares favourably with other methods and analyzes the computational complexity and discusses how new classes could be added to the trained recognizer.
Abstract: We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.
2,954 citations
"Novel face recognition algorithm ba..." refers methods in this paper
...In [10], the author respectively used Eigenfaces method and Neural Network method to implement face recognition on the basis of ORL, and the error recognition rate are 10....
[...]
01 May 1995
TL;DR: A critical survey of existing literature on human and machine recognition of faces is presented, followed by a brief overview of the literature on face recognition in the psychophysics community and a detailed overview of move than 20 years of research done in the engineering community.
Abstract: The goal of this paper is to present a critical survey of existing literature on human and machine recognition of faces. Machine recognition of faces has several applications, ranging from static matching of controlled photographs as in mug shots matching and credit card verification to surveillance video images. Such applications have different constraints in terms of complexity of processing requirements and thus present a wide range of different technical challenges. Over the last 20 years researchers in psychophysics, neural sciences and engineering, image processing analysis and computer vision have investigated a number of issues related to face recognition by humans and machines. Ongoing research activities have been given a renewed emphasis over the last five years. Existing techniques and systems have been tested on different sets of images of varying complexities. But very little synergism exists between studies in psychophysics and the engineering literature. Most importantly, there exists no evaluation or benchmarking studies using large databases with the image quality that arises in commercial and law enforcement applications In this paper, we first present different applications of face recognition in commercial and law enforcement sectors. This is followed by a brief overview of the literature on face recognition in the psychophysics community. We then present a detailed overview of move than 20 years of research done in the engineering community. Techniques for segmentation/location of the face, feature extraction and recognition are reviewed. Global transform and feature based methods using statistical, structural and neural classifiers are summarized. >
2,727 citations
"Novel face recognition algorithm ba..." refers background in this paper
...In [6,7], existing research achievement has been introduced comprehensively....
[...]
11 May 2004
TL;DR: A novel approach to face recognition which considers both shape and texture information to represent face images and the simplicity of the proposed method allows for very fast feature extraction.
Abstract: In this work, we present a novel approach to face recognition which considers both shape and texture information to represent face images. The face area is first divided into small regions from which Local Binary Pattern (LBP) histograms are extracted and concatenated into a single, spatially enhanced feature histogram efficiently representing the face image. The recognition is performed using a nearest neighbour classifier in the computed feature space with Chi square as a dissimilarity measure. Extensive experiments clearly show the superiority of the proposed scheme over all considered methods (PCA, Bayesian Intra/extrapersonal Classifier and Elastic Bunch Graph Matching) on FERET tests which include testing the robustness of the method against different facial expressions, lighting and aging of the subjects. In addition to its efficiency, the simplicity of the proposed method allows for very fast feature extraction.
2,191 citations