Considering the degradation and problem that the weight distribution of training targets is wider than average in the traditional AdaBoost algorithm in the process of human face image training, an improved AdaBoost algorithm was proposed based on adjusting margin of error and setting the threshold value. First, the weight values of the samples were updated according to the comparative result between the threshold value and the weight value of the matching errors of the current samples. Then, the emphasis of the training samples was controlled by adjusting the emphasis relation between positive error and negative error. The experimental results showed that different human face image databases and different ratios of positive and negative errors had little effects on the validness of the improved AdaBoost algorithm. Under the positive and negative error ratio of 1:1 in unrestricted face database LFW, the detection rate was 86.7%, which was higher than that of the traditional AdaBoost algorithm; the number of weak classifiers was 116, which was 15 more than that of the traditional AdaBoost algorithm. The results prove that the proposed algorithm suppresses the degradation and the problem that the weight distribution of training targets is wider than average, and effectively improves the detection rate of human face images.

Since the illumination model used in existing methods of blind image forensics could not effectively represent surface lighting effects, Lambert-Phong illumination model was proposed which contained the diffusing and specular reflection of light. Leveraging this illumination model on the tampering detection of infinite light source image, the experimental results show that the illumination direction of different objects in images could be calculated accurately using the proposed illumination model, and the image tampering could be effectively identified.