Depth feature extraction method for three-dimensional model

Abstract

The invention provides a depth feature extraction method for a three-dimensional model. The method includes the steps of firstly, extracting a polar view of a three-dimensional model as training input data of a deep convolutional neural network; secondly, constructing the deep convolutional neural network, and training the polar view; thirdly, inputting the polar view to the deep convolutional neural network for training till the convergence of the deep convolutional neural network, and determining an internal weight of the trained deep convolutional neural network; and fourthly, inputting the polar view of the three-dimensional model whose feature is to be extracted to the trained deep convolutional neural network, and calculating a feature vector of a full-link layer in the deep convolutional neural network as the depth feature of the three-dimensional model whose feature is to be extracted. According to the invention, the deep convolutional neural network is constructed, the weight is corrected through iterations, the residual is reduced, and thus the network converges. After the training is completed, the full-link layer of the convolutional neural network is extracted as the depth feature of the polar view of the three-dimensional model.

Description

technical field [0001] The invention relates to the technical field of three-dimensional model processing, and more specifically, relates to a deep feature extraction method of a three-dimensional model. Background technique [0002] With the rapid development of 3D model processing technology and computer hardware and software, as well as the promotion of multimedia technology and Internet technology, a large number of 3D models are used in various fields, and people's demand for 3D model applications is also increasing. 3D models play an important role in many fields such as e-commerce, architectural design, industrial design, advertising film and television, and 3D games. The 3D models of large-scale data sets need to reuse design and model retrieval in all aspects of social production and life. Therefore, how to quickly and accurately retrieve the target 3D model from the existing various types of 3D model data sets has become the key to be solved urgently. question. ...

AI Technical Summary

Problems solved by technology

[0004] The current feature extraction method based on deep learning has the following problems: for example, the features extracted by the deep learning framework cannot fully express the 3D model information, the high computational complexity brought by the deep network layer and the over-fitting problem of the network, and the network learning time Long and large memory storage space, etc.

Images