To solve the problem of quickly and accurately extracting face content in multi-face scenes, a multi-face foreground extraction method based on skin color learning was proposed. Firstly, a skin color foreground segmentation model based on skin color learning was given. According to the results of the papers of skin color experts, 1 200 faces of the famous SPA database were collected for skin color sampling. The learning model was established to obtain the skin color parameters of each race in the color space. The skin color image was segmented according to the parameters to obtain the skin color foreground. Secondly, the face seed area was segmented by using face feature point learning algorithm and skin color foreground information and with 68 common feature points of the face as the target. And the centers of the faces were calculated to construct the elliptical boundary model of the faces and determine the genetic range. Finally, an effective extraction algorithm was established, and the genetic mechanism was used within the elliptical boundaries of the faces to regenerate the faces, so that the effective face areas were extracted. Based on three different databases, 100 representative multi-face images were collected. Experimental results show that the accuracy of the multi-face extraction results of the proposed method is up to 98.4%, and the proposed method has a significant effect on the face content extraction of medium-density crowds as well as provides a basis for the accuracy and usability of the face recognition algorithm.

To solve the problem of unreasonable structure and low efficiency of the example block-based image inpainting method, a method for face image inpainting based on circular fields of feature parts was proposed. Firstly, according to the distribution of feature points obtained by feature points localization, the face image was segmented into four circular fields to determine feature search domains. Then, in priority model, the attenuation trend of confidence term was changed in form of exponential function, and with the combination of structural gradient term, the priority was constrained by using local gradient information to improve structural connectivity of inpainting result. In the stage of matching patch search, according to relative position between target patch and each circular domain of feature part, the search domain of matching patch was determined to improve search efficiency. Finally, under the standard of structural similarity, face image inpainting with structural connectivity was completed by choosing the best matching patch. Compared with four state-of-the-art inpainting methods, the proposed method has the Peak Signal-to-Noise Ratio (PSNR) of inpainted image increased by 1.219 to 2.663 dB on average, and the time consumption reduced by 34.7% to 69.6% on average. The experimental results show that the proposed method is effective in maintaining structural connectivity and visual rationality of face image, and has excellent performance in accuracy and time consumption of inpainting.

The quality and quantity of learning samples are very important for intelligent data classification systems. But there is no general good method for finding meaningful samples in data classification systems. For this reason, the concept of convex boundary of dataset was proposed, and a fast method of discovering meaningful sample set was given. Firstly, abnormal and incomplete samples in the learning sample set were cleaned by box-plot function. Secondly, the concept of data cone was proposed to divide the normalized learning samples into cones. Finally, each cone of sample subset was centralized, and based on convex boundary, samples with very small difference from convex boundary were extracted to form convex boundary sample set. In the experiments, 6 classical data classification algorithms, including Gaussian Naive Bayes (GNB), Classification And Regression Tree (CART), Linear Discriminant Analysis (LDA), Adaptive Boosting (AdaBoost), Random Forest (RF) and Logistic Regression (LR), were tested on 12 UCI datasets. The results show that convex boundary sample sets can significantly shorten the training time of each algorithm while maintaining the classification performance. In particular, for datasets with many noise data such as caesarian section, electrical grid, car evaluation datasets, convex boundary sample set can improve the classification performance. In order to better evaluate the efficiency of convex boundary sample set, the sample cleaning efficiency was defined as the quotient of sample size change rate and classification performance change rate. With this index, the significance of convex boundary samples was evaluated objectively. Cleaning efficiency greater than 1 proves that the method is effective. The higher the numerical value, the better the effect of using convex boundary samples as learning samples. For example, on the dataset of HTRU2, the cleaning efficiency of the proposed method for GNB algorithm is over 68, which proves the strong performance of this method.

Focused on the low positioning accuracy of Explicit Shape Regression (ESR) for some facical occlusion and excessive facial expression samples, an adaptive window regression method was proposed. Firstly, the priori information was used to generate an accurate face area box for each image, feature mapping of faces was performed by using the center point of the face area box, and similar transformation was performed to obtain multiple initial shapes. Secondly, an adaptive window adjustment strategy was given, in which the feature window size was adaptively adjusted based on the mean square error of the previous regression. Finally, based on the feature selection strategy of Mutual Information (MI), a new correlation calculation method was proposed, and the most relevant features were selected in the candidate pixel set. On the three public datasets LFPW, HELEN and COFW, the positioning accuracy of the proposed method is increased by 7.52%, 5.72% and 5.89% respectively compared to ESR algorithm. The experimental results show that the adaptive window regression method can effectively improve the positioning accuracy of face feature points.

Focused on the problem of low recognition in recognition systems caused by the inaccuracy of input features, an efficient Deep Sparse Auto-Encoder (DSAE) method using Extreme Learning Machine (ELM) for facial features was proposed. Firstly, truncated nuclear norm was used to construct loss function, and sparse features of face images were extracted by minimizing loss function. Secondly, self-encoding of facial features was used by Extreme Learning Machine Auto-Encoder (ELM-AE) model to achieve data dimension reduction and noise filtering. Thirdly, the optimal depth structure was obtained by minimizing the empirical risk. The experimental results on ORL, IMM, Yale and UMIST datasets show that the DSAE method not only has higher recognition rate than ELM, Random Forest (RF), etc. on high-dimensional face images, but also has good generalization performance.

Aiming at the difficult problem of unsupervised or automatic foreground extraction, an automatic foreground extraction method based on genetic mechanism and difference of Gaussian, named GFO, was proposed. Firstly, Gaussian variation was used to extract the relative important regions in the image, which were defined as candidate seed foregrounds. Secondly, based on the edge information of the original image and the candidate seed foregrounds, the contour of foreground object contour was generated according to connectivity and convex sphere principle, called star convex contour. Thirdly, the adaptive function was constructed, the seed foreground was selected, and the genetic mechanism of selection, crossover and mutation was used to obtain the accurate and valid final foreground. The experimental results on the Achanta database and multiple videos show that the performance of the GFO method is superior to the existing automatic foreground extraction based on difference of Gaussian (FMDOG) method, and have achieved a good extraction effect in recognition accuracy, recall rate and F _β index.