求高手帮助 摘要翻译谢谢

Face recognition is widely research and application of a physiological feature recognition technology, after twenty years of development, have made progress in leaps and bounds, the fusion of modern pattern recognition, biometric technology, image engineering, computer intelligence, neural network and so on many disciplines of knowledge. The basic principle is to extract the training set image local feature information as the training pattern of sequence, and then extracted from the test set image local feature information as a test pattern sequence, through the classification to distinguish both information difference, finally gives the judgement result. So the local feature information extraction is the key of face recognition, pattern classification and recognition algorithm is good or bad will also affect the recognition efficiency.

In the study of local two element model LBP ( Loal Binary Pattern ) basis, this paper proposes the use of two-dimensional wavelet analysis, can be the signal or image the time-frequency local feature analysis, using different filter, the difference compared to the local features of information, interested in finding the local information and features such as orientation, an input image from four different directions of decomposed into four sub image, various sub image to obtain the corresponding feature vector, and then select the appropriate sub-block size, on the block after images were local two element pattern encoding, because each sub image feature vector of high dimension features, using a linear subspace theory of feature vectors for dimensionality reduction transformation, better compression face image feature vector, faster, without reducing the recognition efficiency.

In this paper, the method of face recognition, using the improved LBP operator, to obtain images of the more important local information, enhance and highlight the human face of the key points of interest, and the study of wavelet theory algorithm, proposes to the low frequency and high frequency are extracted feature vector, combined with the advantages of two algorithm theory.

Based on Yale face database and the ORL face database . The experimental results indicate that, the proposed method compared with single method LBP recognition efficiency, such as in a variable light conditions and changes in the expression, but also can better identify, able to adapt to a certain intensity of illumination environment, is not sensitive to the change of expression.

Face recognition is widely a biological and physiological study and application of feature recognition technology, after 20 years of development, leap-forward progress has been made, combination of modern pattern recognition, biometric technologies, intelligent, neural networks for image engineering, computer systems, and many other disciplines of knowledge. Fundamentals is a local feature extraction set of training images sequence information as a training mode, and local feature extraction of test set image information as a test pattern sequence, through the classification identification information for both the difference and finally to determine the outcome. Local feature extraction is the key to human face recognition, pattern recognition algorithms may also affect recognition efficiency.In research local II Yuan mode LBP (Loal Binary Pattern) of Foundation Shang, this made using II dimension Wavelet analysis, can on signal or image Shi frequency of local features analysis, using different of filter, comparison differences of local information features, looking for interested in of local information features as directional,, a site entered image from four a different direction decomposition out four a child image, levels child image gets corresponding of features vector, and select suitable of min block number size, Local binary pattern block image separately encoded, because the feature vector characteristics of higher dimensions, feature vector by using the theory of linear subspaces of dimension reduction transformation, better compression feature vector of human faces, faster, identifying efficiency no reduction.Face recognition methods in this article, using the LBP operator improved, gets more important part in the image, enhance and highlight the key points of interest in the face, and research on wavelets theory algorithms, raised on low-frequency and high-frequency extracted feature vectors, respectively, algorithm theory combines the advantages of both.By Yale on the face and ORL face database of experimental results show that this article proposed by the LBP method in relation to a single method to identify efficiencies, or a certain facial expression changes to some variable light conditions, to better identify, able to adapt to a certain light intensity environments, is not sensitive to facial expression changes.

Face recognition is widely research and application of a biological physiological characteristics identification technology, after 20 years of development, has made rapid progress, focuses on modern pattern recognition, biological characteristics of image technology, engineering, computer intelligence, neural network system and so on many of the knowledge of the subject. The basic principle is the extraction of the training set image as the training of local feature information model sequence, and then put the extraction of the test set image as a test of the local feature information model series, and through the classification of the two discriminant information difference, judge the results are given in the end. So local feature information extraction is the key to face recognition, the pattern classification algorithm stand or fall can also affect recognition efficiency.

In the local dual modes LBP (Loal Binary Pattern), and on the basis of this paper put forward the application of two-dimensional wavelet analysis, can signal or image of the local characteristics of time-frequency analysis, use different filter, comparative differences of local information features, looking for interested in local information such as characteristics such as direction, a input image from four different direction decomposition out four's image, all levels of the son of the corresponding image capture feature vector, and then choose the appropriate block size of number, to block the images are Binary mode of local code, because each sub image of characteristic vector characteristic dimension is higher, using the theory of linear space to feature vector for dimension reduction transform, can better compression face image feature vector, faster, recognition efficiency not reduced.

This paper face recognition method, using the improved LBP operator, get the image in more important local information, the key to enhance and outstanding face interest points, and the wavelet theory algorithm, and puts forward the low and high extraction are characteristic vector, combined with the advantages of the two algorithm theory.

Through Yale and ORL face image database in the face image database experimental results show that the presented method compared with single method LBP recognition efficiency raised, such as in a certain variable light condition or certain expressions change, but also a good recognition, can adapt to the environment must be light intensity, expression is not sensitive to changes.