Three-dimensional model search method based on multiple characteristic related feedback

Abstract

The invention relates to a three-dimensional model retrieval method based on multi-feature relevance feedback, comprising the following steps: a server processes each three-dimensional model in a three-dimensional model database to obtain color view arrays; three-dimensional model features are acquired and synthesized to generate a feature database; features of a two-dimensional sketch offered by a computer client are calculated and matched with feathers in the feature database, the distance between the two-dimensional sketch and each three-dimensional model is calculated, the three-dimensional models as a retrieval result are sorted and outputted according to the distance values; the client labels each retrieval result with 'relevance' or 'irrelevance', returns labeled three-dimensional model information to the server, the server learns the information, classifies the three-dimensional database by SVM fusion method, sorts and outputs the three-dimensional models as a retrieval result; the above steps are repeated until a satisfactory three-dimensional model retrieval result is outputted to a user.

Description

Technical field [0001] The invention belongs to the field of multimedia information retrieval, in particular to a three-dimensional complex model retrieval method based on relevant feedback learning. Background technique [0002] Three-dimensional model retrieval is a hot issue in the field of content-based multimedia information retrieval, and it has a wide range of application prospects. Many institutions at home and abroad are working on this direction. With the rapid development of computer graphics and the further application of light field theory, more complex and realistic three-dimensional models appear on the Internet, because complex models have information closer to actual objects, such as more detailed textures, and richer high-levels Semantic and brilliant color information, so it is necessary to develop an effective and fast high-fidelity 3D model retrieval method. The current 3D model retrieval mechanisms are generally divided into two categories: methods centered ...

AI Technical Summary

Problems solved by technology

[0016] The purpose of the present invention is to overcome the shortcomings of existing 3D model retrieval methods for complex and high-fidelity 3D model retrieval, and propose a 3D model retrieval method based on multi-feature correlation feedback, which ensures the integrity and reliability of information acquisition , and greatly reduce the number of color and contour features, ensuring the speed of real-time retrieval; while enhancing the robustness of texture features, it improves the retrieval accuracy of complex 3D models

Images