An image can be divided into foreground part and background part, while the foreground is often the visual center. Due to the large categories and complex situations of foreground part, the image colorization is difficult, thus the foreground part of an image may suffer from poor colorization and detail loss problems. To solve these problems, an image colorization algorithm based on foreground semantic information was proposed to improve the image colorization effect and achieve the purpose of natural overall image color and rich content color. First, the foreground network was used to extract the low-level features and high-level features of the foreground part. Then these features were integrated into the foreground subnetwork to eliminate the influence of background color information and emphasize the foreground color information. Finally, the network was continuously optimized by the generation loss and pixel-level color loss, so as to guide the generation of high-quality images. Experimental results show that after introducing the foreground semantic information, the proposed algorithm improves Peak Signal-to-Noise Ratio (PSNR) and Learned Perceptual Image Patch Similarity (LPIPS), effectively solving the problems of dull color, detail loss and low contrast in the colorization of the central visual regions; compared with other algorithms, the proposed algorithm achieves a more natural colorization effect on the overall image and a significant improvement on the content part.

The existing optical flow estimation methods, which are frequently used in video quality enhancement and super-resolution reconstruction tasks, can only estimate the linear motion between pixels. In order to solve this problem, a new multi-frame compression artifact removal network architecture was proposed. The network consisted of motion compensation module and compression artifact removal module. With the traditional optical flow estimation algorithms replaced with the adaptive separable convolution, the motion compensation module was able to handle with the curvilinear motion between pixels, which was not able to be well solved by optical flow methods. For each video frame, a corresponding convolutional kernel was generated by the motion compensation module based on the image structure and the local displacement of pixels. After that, motion offsets were estimated and pixels were compensated in the next frame by means of local convolution. The obtained compensated frame and the original next frame were combined together as input for the compression artifact removal module. By fusing different pixel information of the two frames, the compression artifacts of the original frame were removed. Compared with the state-of-the-art Multi-Frame Quality Enhancement (MFQE) algorithm on the same training and testing datasets, the proposed network has the improvement of Peak Signal-to-Noise Ratio (Δ PSNR) increased by 0.44 dB at most and 0.32 dB on average. The experimental results demonstrate that the proposed network performs well in removing video compression artifacts.

Minimally invasive endoscopic surgery always remains a challenge due to the complexity of the anatomical location and the limitations of endoscopic vision. An Augmented Reality (AR) navigation system was designed for simulation of pelvic minimally invasive surgery. Firstly, a 3D model of pelvis which was segmented and reconstructed from the preoperative CT (Computed Tomography) was textured mapping with the real pelvic surgical video, and then a surgical video with the ground truth pose was simulated. The blank model was initially registered with the intraoperative video by a 2D/3D registration based on color consistency of visible surface points. After that, an accurate tracking of intraoperative endoscopy was performed using a stereoscopic tracking algorithm. According to the multi-DOFs (Degree Of Freedoms) transformation matrix of endoscopy, the preoperative 3D model could then be fused to the intraoperative vision to achieve an AR navigation. The experimental results show that the root mean square error of the estimated trajectory compared to the ground truth is 2.3933 mm, which reveals that the system can achieve a good AR display for visual navigation.

The Alzheimer's Disease (AD) usually leads to atrophy of hippocampus region. According to the characteristic, a Convolutional Neural Network (CNN) based method was proposed for the diagnosis of AD by using the hippocampu region in brain Magnetic Resonance Imaging (MRI). All the test data were got from the ADNI database including 188 AD and 229 Normal Control (NC). Firstly, all the brain MRI were preprocessed by skull stripping and aligned to a template space. Secondly, a linear regression model was used for age correction of brain aging atrophy. Then, after preprocessing, multiple 2.5D images were extracted from the hippocampus region in the 3D brain image for each object. Finally, the CNN was used to train and recognize the extracted 2.5D images, and the recognition results of the same object were used for the joint diagnosis of AD. The experiments were carried out by using multiple ten-fold cross validation methods. The experimental results show that the average recognition accuracy of the proposed method reaches 88.02%. The comparison results show that, compared with Stacked Auto-Encoder (SAE) method, the proposed method has improved the diagnosis effect of AD in the case of only using MRI.

To effectively solve overhead computing and bandwidth, high complexity problems about user access privileges revoking in cloud-storage service, a cloud-storage privilege revoking optimization mechanism based on dynamic re-encryption (DR-PRO) was proposed. Firstly, based on ciphertext access control scheme of Ciphertext Policy Attribute Based Encryption (CP-ABE), by using (k,n) threshold algorithm of secret sharing scheme, data information was divided into a number of blocks, and then a data information block was dynamically selected to realize re-encryption. Secondly, the user access privilege revoking was finished by the sub-algorithms, including data cutting, data reconstructing, data publishing, data extracting and data revoking. The theoretical analysis and test simulation showed that, based on high security of user information in cloud-storage service, compared with lazy re-encryption mechanism, the average computing and bandwidth decrease of user access privileges revoking was 5% when data file changed; compared with full re-encryption mechanism, the average computing and bandwidth decrease of user access privileges revoking was 20% when shared data block changed. The experimental results show that DR-PRO effectively improves the performance and efficiency of user access privileges revoking in cloud-storage service.

Concerning the problem that videos images captured from coal mines filled with coal dust and mist are often with quality problems such as lots of noise, low resolution and blur. To solve this problem, an enhancement algorithm for fog and dust images in coal mine based on dark channel prior theory and bilateral adaptive filter was proposed. On the basis of dark channel prior, the softmatting process was replaced with the adaptive bilateral filtering to obtain fine transmittance map. Then according to the special circumstances of coal mines, the global atmosphere light and the rough transmittance map were got from new perspective and image denoising was realized on the basis of the image degradation model. The experiment results show that the image processing time for a resolution of 1024×576 is 1.9 s. Compared with He algorithm (HE K, SUN J, TANG X. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(12):1-13.), the efficiency increased 5 times.Compared with other algorithms such as histogram equalization method, the proposed algorithm is effective to enhance the image detail. In this way, images can be more suitable for human vision as a whole.

To achieve efficient software testing under cloud computing environment, a method of generating parallel test cases automatically for functional testing of Web application system was proposed. First, parallel test paths were obtained by conducting depth-first traversal algorithm on scene flow graph; then parallel test scripts were assembled from test scripts referred by the test paths, and parameterized valid test data sets that can traverse target test paths and replace test data in script were generated using Search Based Software Testing (SBST) method. A vast number of automatic distributable parallel test cases were generated by inputting test data into parallel test scripts. Finally, a prototype system of automatic testing in cloud computing environment was built for examination of the method. The experimental results show that the method can generate a large number of valid test cases rapidly for testing in cloud computing environment and improve the efficiency of testing.

Hot topic mining is an important technical foundation for monitoring public opinion. As current hot topic mining methods cannot solve the affection of word noise and have single hot degree evaluation way, a new mining method based on topic cluster evaluation was proposed. After forum data was modeled by Latent Dirichlet Allocation (LDA) topic model and topic noise was cut off, the data were then clustered by improved cluster center selection algorithm K-means++. Finally, clusters were evaluated in three aspects: abruptness, purity and attention degree of topics. The experimental results show that both cluster quality and clustering speed can rise up by setting topic noise threshold to 0.75 and cluster number to 50. The effectiveness of ranking clusters by their probability of the existing hot topic with this method has also been proved on real data sets tests. At last a method was developed for displaying hot topics.

The multicast QoS (Quality of Service) routing problems was introduced, and then a novel QoS-based multicast routing algorithm based on the neural networks (NN) and the genetic algorithm (GA) was proposed. A novel coding scheme was also developed, which is very easy for the crossover and mutation. By this mean, it can overcome premature and increase the convergence speed. The simulation results show that the proposed algorithm outperforms the traditional GA in terms of convergence speed.