Target image quick retrieval method and system based on artificial intelligence
A target image and artificial intelligence technology, applied in still image data retrieval, neural learning methods, still image data query, etc., can solve poor generalization performance, cannot distinguish confusing features, and does not consider mining image similarity relations And other issues
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] This embodiment provides an artificial intelligence-based method for fast retrieval of target images;
[0030] Such as figure 1 As shown, the fast retrieval method of target image based on artificial intelligence includes:
[0031] S101: Obtain a template image and several known tags corresponding to the template image;
[0032] S102: extract the image to be detected from the target image database;
[0033] S103: Input the image to be detected and the template image into the trained convolutional neural network respectively, and output the hash code of the image to be detected and the hash code of the template image;
[0034] S104: Based on the Hamming distance between the hash code of the image to be detected and the hash code of the template image, the similarity between the image to be detected and the template image is obtained. The smaller the Hamming distance, the higher the similarity, and the higher the similarity is selected. at the set threshold (set the thres
Embodiment 2
[0091] This embodiment provides an artificial intelligence-based target image fast retrieval system;
[0092] A fast retrieval system for target images based on artificial intelligence, including:
[0093] An acquisition module configured to: acquire a template image and several known labels corresponding to the template image;
[0094] An extraction module configured to: extract an image to be detected from a target image database;
[0095] A conversion module configured to: input the image to be detected and the template image into the trained convolutional neural network, and output the hash code of the image to be detected and the hash code of the template image;
[0096] An output module configured to: obtain the similarity between the image to be detected and the template image based on the Hamming distance between the hash code of the image to be detected and the hash code of the template image, the smaller the Hamming distance, the greater the similarity High, select one
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap