Study On Non-linear Correlation Filter Bank And Sparse Representation Face Recognition Algorithms

With the development of science and technology,information security plays an irreplaceable role in our daily life which leads to more and more public attention to identity recognition.Face recognition technology has grown rapidly in recent years,Which has attracted a large number of researchers.Although the accuracy of face recognition is getting higher and higher,which is affected by external factors easily,therefore this problems will be a breakthrough for face recognition.As we known,some important characteristic information of the face image may be lost,which under the change of light,posture and facial expression.In order to improve this situation.We proposed a face recognition method based on nonlinear correlation filter bank.The new algorithm uses the advantage that the face image is segmented into a number of non-overlapping sub-modules that do not overlap,which have correspondingly generated correlation filters and sigmoid functions extend the uniform dynamic range to enhance the contrast of the image to making this algorithm have a strong robustness.The results show that the algorithm has been significant improve the accuracy of recognition rate.On the other hand,there are occluded objects and other unconstrained external environmental conditions will affect the accrauracy of recognition rate.We proposes the combination of LRC and CRC deviation based on mirror image for face recognition.First the method generates mirror images,Then by merging the original face image and the mirror image to form a new mixed training samples,LRC and CRC produce residuals in very different ways,but they both use residuals to perform classification.Therefore,by combining the residuals of these two methods,better performance for face recognition can be achieved.In this paper,a simple weighted sum based fusion scheme is proposed to integrate LRC and CRC for more accurate recognition of faces.