Three-dimensional model classification retrieval method based on kernel sparse representation

Abstract

The invention discloses a three-dimensional model classification retrieval method based on kernel sparse representation. The method comprises the following steps: 1, carrying out vertex simplificationprocessing on a three-dimensional model represented in a point cloud form by using an edge shrinkage algorithm based on a secondary error as a measurement cost; 2, calculating the direction of the three-dimensional model after vertex simplification, ensuring that the same kind of models can be aligned in the direction, and obtaining three characteristic direction vectors of the three-dimensionalmodel through calculation; 3, rendering the three-dimensional model based on the three characteristic direction vectors to obtain a plurality of different rendered images in corresponding different directions; 4,for the characteristics of the three-dimensional model in different data sets, comprehensively considering data characteristics and descriptor characteristics, and selecting a characteristic descriptor to extract the characteristics of the rendered image; and 5, matching the extracted feature vectors by using an improved kernel sparse representation classifier so as to realize the classification retrieval work of the three-dimensional model. The method has certain robustness, and relatively high-efficiency and reliable superior performance is obtained.

Description

technical field [0001] The 3D model classification and retrieval method based on kernel sparse representation belongs to the field of computer vision, especially using kernel techniques to implement sparse representation classifiers in new feature spaces, and extends its applicable scenarios from 2D data to 3D data. Background technique [0002] In recent years, with the rapid development of computer technology, 3D modeling technology has become increasingly mature. Along with this upsurge, 3D models have gradually developed into the fourth-generation multimedia data type after sound, image and video. At present, the 3D models on the Internet are growing exponentially, and at the same time, they have been widely used in many fields, such as scientific research, industry and medicine. It can be seen everywhere in our life, such as playing an important role in virtual environment, computer-aided design, 3D games, film and television animation, molecular biology, geographic in...

AI Technical Summary

Problems solved by technology

However, SRC will lose the ability to classify data distributed in the same direction

Images