Clothing attribute identification method based on migration significance prior information
A priori information and attribute recognition technology, which is applied in the field of computer vision and deep learning, can solve the problems of increasing the difficulty of method generalization in the application of the method, so as to improve the generalization ability, improve the recognition accuracy and reduce the labor cost.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0042] A clothing attribute recognition method based on transfer salience prior information, specifically comprising the following steps:
[0043] Step S1: Obtain the image data of the clothing image for attribute annotation, and perform preprocessing and enhancement operations on the clothing image;
[0044] Step S2: The clothing image is input to the saliency detection network for saliency prediction, and the saliency map of the clothing image is obtained, which is superimposed with the clothing image to form a clothing image with saliency prior information;
[0045] Step S3: Perform steps S1-S2 for each clothing image to obtain clothing images with significant prior information corresponding to all clothing images, and input clothing images with significant prior information corresponding to all clothing images to the classification convolutional neural network Train until the classification convolutional neural network converges;
[0046] Step S4: When performing online r...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com