Research On Face Recognition Based On LBP And Two Dimensional Principal Component Analysis

Face recognition includes many subjects such as image processing,pattern recognition,artificial intelligence,it has been one of most active and challenging task in computer vision and pattern.In the information time,how to recognize and identify a person accurately and to protect information security has been become a key social problem that must to be solved.Face recognition technology has got very wide application prospects with its unique advantages such as simple and intuitive,difficult copy,high safety,easy operation etc.However,the stand or fall of feature extraction has a crucial influence to the result of face recognition.Therefore,how to extract the stable and effective facial features that contains class information as much as possible to recognition,and how to combining a variety of different features to achieve more ideal classification results are all the research hotspots of current face recognition.With reading a lot of domestic and foreign the exsiting relevant literatures,this paper summarizes the previous research results and studies the feature extraction methods based on the local binary pattern and histogram of oriented gradient,At the same time,The application of two-dimensional principal component analysis(PCA)in face recognition is deeply analyzed.The main work is as follows.1.Local binary pattern has limitation in extracting texture feature and cannot effectively depict the edge and direction information.Considering the advantages and disadvantages of local binary model and histogram of oriented gradient,In this paper,a novel method was proposed that addressed the problems by fusing HOG and Adaptively weighted Histograms of Oriented Gradients.Firstly,the image is divided into sub-images,Get the information entropy and LBP feature for each sub-images.After that,the feature of the sub-images is combined into the complete feature of the image.At the same time,the image is extracted by HOG,and the features extracted from the last two are merged to obtain effective facial features.Experiments on ORL and Yale face database show that the proposed method is better than just single LBP,HOG,and also improves the accuracy of face recognition,The accuracy rate was 93.75%.2.2DPCA methods and support vector machines(SVM)are studied in depth,The performance analysis and test of 2DPCA and SVM are carried out respectively,The influence of different feature dimensions and sample size on the recognition rate of two-dimensional principal component analysis was analyzed,selection of optimum parameters testing of the SVM kernel function.Based on the analysis and test,the experiment of face recognition based on 2DPCA and support vector machine(SVM)is carried out and a static face recognition system based on 2DPCA and SVM is implemented.