AN EFFICIENT DEVELOPMENT OF FACE SPOOFING DETECTION METHOD USING IMAGE DISTORTION ANALYSIS Dr.B.CHELLAPRABHA

In recent years face recognition has been the important factor in biometric authentication. Significant progress has been made in the area of face spoofing detection. In practical application, the problem of spoofing attacks can be threatened to face biometric systems which is used for authentication. Kernel Discriminate Analysis(KDA) is effective in detecting the face spoofing detection. Kernel Discriminate Analysis uses two techniques, MultiScale Binarized Statistical Image Features on Three Orthogonal Planes (MBSIF-TOP) and MultiScale Local Phase Quantization on Three Orthogonal Planes(MLPQTOP).MBSIF-TOP is effective in detecting spoofing attacks, showing promising performance compared to existing alternatives. Next, by combining MBSIFTOP with a blur-tolerant descriptor, namely Multiscale Local Phase Quantization representation (MLPQ-TOP), the robustness of the spoofing attack improved. The fusion of the information provided by MBSIF-TOP and MLPQ-TOP is realized via a kernel fusion approach based on a kernel Discriminant Analysis technique. But it avoids the costly eigen analysis computations by solving the KDA problem, So it fails to detect the low quality images. The proposed work use a technique called Image Distortion Analysis (IDA) which is effective in detecting spoofing in the low quality images. It is very efficient texture operator which labels the pixels of an image by thresholding the neighbourhood of each pixel and if the threshold value below the setting pixels then it detected as low quality images. Spoofing has done in low quality images. Then IDA compares the original image with the spoofed image and find the percentage of spoofing has done in that image.