Aiming at the problems that existing image deblurring algorithms suffer from diffusion and artifacts when dealing with edge loss and the use of full-frame deblurring in video processing does not meet real-time requirements， an Adaptive DeBlurring Generative Adversarial Network （ADBGAN）algorithm based on active discrimination mechanism was proposed. Firstly， an adaptive fuzzy discrimination mechanism was proposed， and an adaptive fuzzy processing network module was developed to make a priori judgment of fuzziness on the input image. When collecting the input， the blurring degree of the input image was judged in advance， and the input frame which was clear enough was eliminated to improve the running efficiency of the algorithm. Then， the incentive link of the attention mechanism was introduced in the process of fine feature extraction， so that weight normalization was carried out in the forward flow of feature extraction to improve the performance of the network to recover fine-grained features. Finally， the feature pyramid fine feature recovery structure was improved in the generator architecture， and a more lightweight feature fusion process was adopted to improve the running efficiency. In order to verify the effectiveness of the algorithm， detailed comparison experiments were conducted on the open source datasets GoPro and Kohler. Experimental results on GoPro dataset show that the visual fidelity of ADBGAN is 2.1 times that of Scale-Recurrent Network （SRN） algorithm， the Peak Signal-to-Noise Ratio （PSNR） of ADBGAN is improved by 0.762 dB compared with that of SRN algorithm， and ADBGAN has good image information recovery ability； in terms of video processing time，the actual processing time is reduced by 85.9% compared to SRN.The proposed algorithm can generate deblurred images with higher information quality efficiently.

The existing endoscopic image highlight removal algorithms often have some problems such as unreasonable removal structure and color distortion， which leads to the wrong results of the focus recognition algorithms and image enhancement algorithms. In order to solve the above problems， in the aspect of highlight localization， a method based on the combination of growth in dark region and Scharr filtering was proposed to locate relative highlight； in the aspect of highlight filling， an improved Crinminisi algorithm was proposed. Firstly， through the statistics on a huge amount of data， the search scope was limited and the filling efficiency was increased. Secondly， the statistical scope of priority was improved to avoid repeated meaningless calculations. Finally， the reasonable reconstruction of texture was performed according to the adaptive templates of different regions. Experiments were carried out on endoscopic image dataset of different human tissues， compared with the dichromatic reflection model based method， the Robust Principle Component Analysis （RPCA） method， the thermal diffusion method and the original Criminisi algorithm， the Natural Image Quality Evaluator （NIQE） value of the proposed algorithm was the lowest. Compared with the RPCA method， the thermal diffusion method and the original Crimnisi algorithm， the running time of the proposed algorithm was the lowest. Experimental results show that the proposed algorithm not only has better objective image indicators than other algorithms， but also has a nearly 100-fold improvement in efficiency compared to the original Criminisi algorithm.

Focusing on the issue that most of existing approaches need sentiment lexicon annotated manually to extract sentiment features, a sentiment analysis method of product reviews based on Contrastive Divergence-Restricted Boltzmann Machine (CD-RBM) deep learning was proposed. Firstly, product reviews were preprocessed and represented as vectors using the bag-of-words. Secondly, CD-RBM was used to extract the sentiment features from product review vectors. Finally, the sentiment features were classified with Support Vector Machine (SVM) as the sentiment analysis result. Without any manually pre-defined sentiment lexicon, CD-RBM can automatically obtain the sentiment features of higher semantic relevance; combining with SVM, the correctness of the sentiment analysis result is guaranteed. The optimum training period of RBM was experimentally determined as 10. In the comparison experiments with methods including RBM, SVM, PCA+SVM and RBM+SVM, the combination method of CD-RBM feature extraction and SVM classification shows the best precision and best F-measure, as well as better recall.

To reduce the influence of the noise on the measurement accuracy of the six-axis force sensor and solve the problem that the standard Kalman filter can not gain the optimal estimation because of the state-space model error of the sensor, a new adaptive Kalman filtering with two adaptive factors was proposed. The augmented state-space model of colored noise for lower E-type membrane based on the relationship between the response of sinusoidal excitation force and the strain was established. Based on the principle of standard Kalman filter, the impact of model errors on the filter estimate results were analyzed. The technology of dynamically adjusting the weight of state prediction in the filter estimation was introduced. The adaptive Kalman filter estimation principle and the recursion formula were presented. Finally, the dual adaptive factors were constructed through the model of three-section function on the basis of orthogonality principle and least square method. The simulation results indicate that comparing with the strong tracking filter and standard Kalman filter, the proposed algorithm has better estimate accuracy and stability. It can effectively enhance the measurement accuracy of six-axis force sensor and control the influence of model errors.