The second is how to realize automatic content analysis and extract visual and semantic features to describe video content 12. One of the problems is video structure, that is, how to automatically realize video frequency time-domain segmentation, and segment the video stream into different levels of video units with certain significance. How to process the image information by deep residual group and draw the image by deep learning model, and then repair the image 7, 8, and successfully tested in the application 9, 10, 11. Real image reproduction is a processing technology to enable imaging equipment to provide ideal images in line with human physiological visual perception 6.Īt present, people have carried out a lot of research work on the difficulties of visual perception technology, and made many breakthroughs. The problem of image resolution reconstruction can be improved by using deep neural network to process feature data 5. Image completion can often reproduce the lost information 3, and image completion can fill the defects of the picture when the target features are seriously missing 4. Computer vision is using computer simulated biological vision system for environmental awareness and understanding, and visual perception as a first step in computer vision system for image processing, computer vision is one of the core technology items 2. In recent years, with the acceleration of information process and the rapid development of computer technology, people's demand for computer vision in life and production is becoming more and more urgent 1. Compared with the traditional PCNN algorithm, it has the advantages of fast visual perception and clear target contour segmentation, and effectively improves the anti-interference performance of the model.
#Construct diag matlab series#
Digital experiments show that the multi-scale multi-task pulse coupled neural network model can shorten the total training time by 17 h, improve the comprehensive accuracy of the task test data set by 1.04%, and shorten the detection time of each image by 4.8 s compared with the series network model of multiple single tasks. In addition, the spatial and gray value differences of pixels should be considered comprehensively to determine their connection matrix.
The feature extraction and object segmentation properties of PCNN come from the spike frequency of neurons, and the number of neurons in PCNN is equal to the number of pixels in the input image. From the coupling characteristics of PCNN, junction close space of image and gray level characteristics, it determined the local gray mean square error of image connection strength coefficient. Firstly, it used the improved immune genetic algorithm to adaptively obtain the optimal threshold, and then replaced the dynamic threshold in PCNN model with the optimal threshold, and finally used the pulse coupling characteristics of PCNN model to complete the image segmentation. In order to solve this problem, this paper proposed an IGA-PCNN image segmentation method combining the improved algorithm and PCNN model. The genetic algorithm improves the loop termination condition and the adaptive setting of model parameters of PCNN image segmentation algorithm, but the PCNN image segmentation algorithm still has the problem of complexity. The PCNN image segmentation method based on genetic algorithm is analyzed. In the simulation process, the initial threshold is optimized by the two-dimensional maximum inter-class variance method, and in order to improve the real-time performance of the algorithm, the fast recurrence formula of neural network is derived and given.
The model firstly analyzes the structure and generalization ability of neural network multi-class classifier, uses the minimax criterion of feature space as the splitting criterion of visual perception decision node, which solves the generalization problem of neural network learning algorithm. Based on pulse coupled neural network (PCNN) theory, this paper constructs a visual perception model framework and builds a real image reproduction platform. Pulse-coupled neural networks perform well in many fields such as information retrieval, depth estimation and object detection.
0 kommentar(er)
