To solve the problems in face editing， such as unnatural editing results and great changes in generated images， a controllable face editing algorithm with closed-form solution was proposed. Firstly， n latent vectors were sampled randomly to construct a sample matrix， and the top k principal component vectors of the matrix were calculated. Then， five attributes of face image were obtained by ResNet-50， and the semantic boundary of each attribute was calculated by Support Vector Machine （SVM）. Finally， the interpretable direction vectors of these attributes were calculated， which were as closed to the principal components vectors as possible and stayed as far away from the semantic boundary of the corresponding attribute as possible at the same time， thereby reducing the coupling between facial attributes， and improving the controllability in face editing. Because the algorithm has a closed-form solution， it has high efficiency. Experimental results show that the compared with closed-form Factorization of latent Semantics in GANs （SeFa） algorithm and Discovering Interpretable Generative Adversarial Network Controls （GANSpace） algorithm， the proposed algorithm increases the Inception Score （IS） by 19% and 26% respectively， decreases the Fréchet Inception Distance （FID） by 4% and 37% respectively， and decreases the Maximum Mean Discrepancy （MMD） by 15% and 48% respectively. It can be seen that this algorithm has good controllability and decoupling.

With the significant increase of computation-intensive and latency-intensive applications， Mobile-Edge Computing （MEC） was proposed to provide computing services for users at the network edge. In view of the limited computing resources of edge servers at the Base Stations （BSs） and the long latency of long-distance computation offloading of users at the network edge， a multi-user computation offloading and resource optimization policy based on Device-to-Device （D2D） communication was proposed. The D2D was integrated into MEC network to directly offload tasks to neighbor users for executing in D2D mode， which was able to further reduce offloading latency and energy consumption. Firstly， the joint optimization problem of multi-user computation offloading and multi-user computing resource allocation was modelled with the optimization objective of minimizing the total system computing cost including latency and energy consumption. Then， the solution of this problem was considered as a D2D pairing process， and the multi-user computation offloading and resource optimization policy algorithm was proposed based on stable matching. Finally， the optimization allocation policy of D2D offloading was solved iteratively. The characteristics such as stability， optimality and complexity of the proposed algorithm were analyzed by theoretical proof. Simulation results show that， the proposed algorithm can effectively reduce the total system computing cost by 10%-30% compared with the random matching algorithm， and the performance of the proposed algorithm is very close to the optimal exhaustive search algorithm， indicating that the proposed policy based on D2D offloading is helpful to improve latency and energy consumption performance.

How to effectively identify all kinds of attacked faces is an urgent problem to be solved in the process of face recognition. The face anti-spoofing methods based on deep learning have high performance， but also bring a large number of parameters and calculation， so they cannot be deployed in mobile or embedded devices. To solve the above problems， a face anti-spoofing method based on regional blocking and lightweight network was proposed. Firstly， the training samples were randomly blocked. Then， a lightweight network based on attention mechanism was designed for feature extraction and image classification. Finally， in order to improve the detection accuracy， data augmentation was conducted on the test samples based on regional blocking. Experimental results show that the proposed model reaches 100% accuracy on REPLAY-ATTACK and CASIA-FASD datasets. At the same time， the proposed model obtains 99.49% accuracy and 0.458 0% Average Classification Error Rate （ACER） on the Depth modal of CASIA-SURF dataset， which are much better than those obtained by convolutional neural networks such as ResNet and ShuffleNet. And the parameter amount of the model is only 0.258 2 MB. In practical applications， the end-to-end lightweight network structure makes the proposed model easier to be deployed on mobile devices for real-time face anti-spoofing detection.

Given proper values of shift windows in spatial domain and color domain respectively, the color data were filtered by means of Mean-Shift clustering, during which the color data in the rcircular neighboring domain of current data point were used as the clustering samples. Then image data at current position were updated with the cluster center newly obtained. This algorithm overcomes the difficulty to choose proper window radius for the model of Mean-Shift filtering combining spatial domain and color domain to adopt the possible variation of image size. Finally, the experimental results verify the validity of MeanShift filtering.