Analysis of Face Spoof Detection Technique

The face spoof technique was proposed to identify and detect the spoofed and non-spoofed images. The DWT technique is used to analyze the textual features present within the test images. There is a possibility that some exceptional disturbances are available like geometric disturbances and the artificial texture disturbances. The camera and the illumination subordinates are mostly responsible for such disturbances. A perfect camera with no defects should be used just to notice the difference between the geometric, the illumination and the texture based disturbances. To detect the whether the image is spoofed or non-spoofed already existed technique SVM classifier is used. The SVM based technique is proposed in the previous work for the detection of face spoof. The face spoof detection techniques are based on two steps; the first step is of feature extraction and second is of classification. The Eigen based technique is applied for the feature extraction and SVM classifier is applied for the classification. To improve accuracy of the face spoof detection SVM classifier will be replaced with the KNN classifier.