Aiming at the problems of low accuracy and poor robustness of traditional point cloud registration algorithms and the inability of accurate radiotherapy for cancer patients before and after radiotherapy， an Attention Dynamic Graph Convolutional Neural Network Lucas-Kanade （ADGCNNLK） was proposed. Firstly， residual attention mechanism was added to Dynamic Graph Convolutional Neural Network （DGCNN） to effectively utilize spatial information of point cloud and reduce information loss. Then， the DGCNN added with residual attention mechanism was used to extract point cloud features， this process was not only able to capture the local geometric features of the point cloud while maintaining the invariance of the point cloud replacement， but also able to semantically aggregate the information， thereby improving the registration efficiency. Finally， the extracted feature points were mapped to a high-dimensional space， and the classic image iterative registration algorithm LK （Lucas-Kanade） was used for registration of the nodes. Experimental results show that compared with Iterative Closest Point （ICP）， Globally optimal ICP （Go-ICP） and PointNetLK， the proposed algorithm has the best registration effect with or without noise. Among them， in the case without noise， compared with PointNetLK， the proposed algorithm has the rotation mean squared error reduced by 74.61%， and the translation mean squared error reduced by 47.50%； in the case with noise， compared with PointNetLK， the proposed algorithm has the rotation mean squared error reduced by 73.13%， and the translational mean squared error reduced by 44.18%， indicating that the proposed algorithm is more robust than PointNetLK. And the proposed algorithm is applied to the registration of human point cloud models of cancer patients before and after radiotherapy， assisting doctors in treatment， and realizing precise radiotherapy.

Aiming at the complexity of image background and difficulty of feature point extraction in cattle body size measurement based on machine vision， a new cattle body size measurement method based on Kinect v4 sensor was proposed. In this method， the color and depth images were collected， and the body size data were calculated by the body feature points extracted by the combination of algorithms such as object detection， Canny edge detection， and three-point arc curvature. Firstly， an image dataset of feature parts of cattle body size was created， and the deep learning You Only Look Once v5 （YOLOv5） target detection algorithm was used to detect feature part information of cattle body size in order to reduce the interference of other parts of cattle body and background on the extraction of body size measuring points. Secondly， with the help of Canny edge detection， contour extraction and other image processing algorithms in Open source Computer Vision （OpenCV） image processing library， the key contours with measuring points of cattle body size were obtained. Then， the algorithms such as polynomial fitting and three-point arc curvature were performed on the key contours to extract the measuring points of cattle body size in two-dimensional image. Finally， the depth information was used to convert the measuring point information in two-dimensional image to three-dimensional coordinate system， and the cattle body size measurement method was designed in three-dimensional coordinate system with the RANdom SAmple Consensus （RANSAC） algorithm. Through the comparison between the experimental measurement results with the sensor and the side of cattle body at different angles and manual measurement results in a complex environment， it can be seen that the average relative error of withers height is 0.76%， the average relative error of body oblique length is 1.68%， the average relative error of body straight length is 2.14 %， and the average relative error of hip height is 0.76% in cattle body measurement data. Experimental results show that the proposed method has high measurement accuracy in complex environment.

In data layer, the course model and resource model were built based on Markov chain and vector space model, and the teacher model was built based on teachers' personal registration information and nodes of course model. In off-line layer, the content features of course model and resource model were extracted via Term Frequency-Inverse Document Frequency (TF-IDF) algorithm, and the course model and resource model of data layer were initialized and optimized. Then relations between any two resources or recourse and course were calculated using association rules mining and similarity measure, and intermediate recommendation results were given using teacher model and course model. A weighted hybrid recommendation algorithm was proposed to generate recommendation list in on-line layer. The proposed system has been successfully applied in a real education resources sharing platform which consists of 600 thousand teaching resources.

For the sensitivity of the portal vein data to classical liver functional segmentation method, a liver segment method based on hierarchical vascular tree combining with the Couinaud theory and portal vein distribution characteristics is proposed. Firstly, liver and vessels are extracted from the abdominal CT image by image segmentation and skeletonization methods. Secondly, secondary subtree set was determined through statistical analysis on average radius of vascular branches, so as to divide the secondary subtree set into several different classes by k-means++ clustering algorithm according to their own blood-supply area. Thirdly, a nearest neighbor segment approximation algorithm was used to segment the liver into parts. Finally, the internal anatomical structure of liver and its vascular system was demonstrated using three-dimensional visualization technology, and then making annotations on liver segments to extract clinical interest information. Experimental result shows that the method can obtain good results when vascular tree contains plenty branches and complex structure. Furthermore, for considering the impact of major secondary branches, the final liver segment distribution and attribute results are in line with the Couinaud liver segment theory.

To synthesize facial pose and expression images simultaneously from one image, a tensor-based subspace projection method for synthesizing multi-pose and expression face images was proposed. Firstly, the forth order texture tensor and shape tensor were created from the feature annotated images respectively. Then a tucker tensor decomposition technique was applied to build projection subspaces (person, expression, pose and feature subspaces). Core tensors, expressions, poses and feature subspaces were organized into a new tensor properly which was used for synthesizing new facial poses and expressions. The proposed method took full advantage of the intrinsic relationship among the facial affected various factors. The experimental results show that the proposed method can synthesize different facial expressions with kinds of poses of the face using a known facial expression and pose image.

The temporal domain characteristic of the infrared image and different features of small targets, noise and background were analyzed in this paper. A new infrared small target detection algorithm combining temporal domain and spatial domain was put forward. Because of the slow change of background, the Signal-to-Noise Ratio (SNR) of the small target was first enhanced through subtracting the conjoint frames. Then the potential small targets were detected by applying the centre distinguishing method, and the two-sliding-window algorithm was adopted to remove the isolated noise. At last, the similarity distinguishing method was used to eliminate the edge disturbance and the final detection of the small target was realized. The experimental results indicate that the improved algorithm has better target detection and real-time performance.