A method and system for image similarity recognition based on multi-feature fusion

By employing a multi-feature fusion and progressive feature extraction method for image similarity recognition, and dynamically adjusting computational depth and resource allocation, the problems of resource waste and low efficiency in existing technologies are solved, achieving efficient and accurate image similarity recognition.

CN121074444BActive Publication Date: 2026-04-03BEIJING JINHUI TECH CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202511283370.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-09-09
Publication Date
2026-04-03
Estimated Expiration
2045-09-09

AI Technical Summary

Technical Problem

In existing technologies, image similarity recognition methods suffer from wasted computational resources and low processing efficiency when processing different types of images. In particular, computational resources are wasted severely for images with obvious feature differences, and the recognition accuracy is unstable.

Method used

An image similarity recognition method based on multi-feature fusion is adopted. It extracts features progressively from perceptual hash values, local features and deep learning features, combines them with weight coefficients for feature fusion, dynamically adjusts the computation depth, and optimizes data access efficiency through image size grouping management and parallel computing task scheduling.

Benefits of technology

It achieves improved computational efficiency and resource utilization while ensuring recognition accuracy. In particular, it can quickly and accurately identify images with obvious feature differences, and improves retrieval efficiency and accuracy in large-scale image databases.

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

Abstract

A method and system for image similarity recognition based on multi-feature fusion, relating to the field of image processing technology, is disclosed. The method includes: calculating the hash features of an input image and generating hash similarity and hash confidence values; when the hash confidence value is less than a hash confidence reference value, performing local feature extraction on the input image to generate local similarity and local confidence values; when the local confidence value is less than the local confidence reference value, performing deep learning feature extraction on the input image to obtain deep features and deep confidence values; determining the weight coefficients of the hash features, local features, and deep features based on the hash confidence value, local confidence value, and deep confidence value, respectively; performing feature fusion to generate a fused feature vector; and calculating the final similarity between the input image and the image to be compared based on the fused feature vector. Implementing this application can improve processing efficiency while ensuring the accuracy of image similarity recognition.
Need to check novelty before this filing date? Find Prior Art