View-based spatial shape recognition method, device, equipment, and storage medium

By obtaining multiple perspective views of the target product, extracting the structural contour map and using Hu moments and Fourier descriptors for feature extraction, combined with classification models and multi-image fusion rules, the problem of unreliable retrieval results in traditional image search engines is solved, and higher image retrieval accuracy is achieved.

CN115272689BActive Publication Date: 2025-09-30XIAMEN UNIV OF TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202210866401.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-22
Publication Date
2025-09-30
Estimated Expiration
2042-07-22

AI Technical Summary

Technical Problem

Traditional image search engines perform searches based on metadata information surrounding the image, resulting in unreliable search results that cannot meet the specific needs of users. In addition, image retrieval based on visual features ignores the relationship between the various views in the appearance patent design, reducing the accuracy of image searches.

Method used

By obtaining views of the target product from multiple perspectives, extracting the structural contour map, using Hu moment and Fourier descriptor for feature extraction, combining classification model and multi-image fusion rules, the spatial shape of the target product can be identified.

Benefits of technology

It improves the accuracy of image retrieval, provides a more reliable retrieval basis, and can more accurately identify the spatial shape of the target product.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Embodiments of the present invention provide a view-based spatial shape recognition method, apparatus, device, and storage medium, relating to the field of appearance recognition technology. This spatial shape recognition method includes S1, obtaining views of a target product from N perspectives. S2, extracting structural contour images of X structures of the target product from N perspectives based on the views from N perspectives. S3, performing feature extraction based on the structural contour images to obtain the Hu moments and Fourier descriptors of the X structures from N perspectives. S4, obtaining feature vectors of the X structures from N perspectives based on the Hu moments and Fourier descriptors. S5, classifying the feature vectors using a classification model to obtain the plane shapes of the X structures from N perspectives. S6, performing recognition based on the plane shapes using multi-image fusion rules to obtain the spatial shapes of each structure of the target product. The spatial shape recognition method of the present invention can obtain spatial shapes based on views, thereby providing a new retrieval basis for image retrieval.
Need to check novelty before this filing date? Find Prior Art