Wenhao Wen
Deep convolutional neural network (Deep-CNN), graph parsing, unsupervised methods, attention mechanism, feature extraction
With the rapid development of computer image processing technology, accurate image parsing in graphics has become a hot issue. Traditional image-in-graph parsing methods usually rely on a large amount of labelled data for training and optimisation, which obviously reduces the efficiency and accuracy of image-in-graph analysis. In order to solve these problems, the study first uses unsupervised methods and attention mechanisms to annotate the features of the image-in-graph; on the basis of the annotation, deep convolutional neural networks are used to parse the image-in- graph, and the parsing model is constructed; and finally, simulation experiments are used to validate the performance of the model in image parsing. The results show that the image parsing model in graphics in the image information labelling accuracy and labelling recall are 95.31% and 97.28%, respectively. Meanwhile, the accuracy and F1 value of the image parsing model in graphical feature recognition are 94.58% and 0.92, respectively, which are better than the comparison methods. This indicates that the graph parsing model constructed in the study can significantly improve the accuracy and efficiency of graph parsing. At the same time, it reduces the dependence on a large amount of labelled data and can now improve the analysis and processing ability of graphics.
Important Links:
Go Back
