Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image recognition method and device

An image recognition and image technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve the problem of weak distinction of semantic knowledge and achieve the effect of improving recognition ability

Active Publication Date: 2020-07-28
UNIV OF SCI & TECH OF CHINA +1
View PDF10 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the weak discriminative nature of semantic knowledge, it is difficult for this semantically aligned visual representation to separate the two domains, therefore, images of unknown domains are more likely to be recognized as known domain categories

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image recognition method and device
  • Image recognition method and device
  • Image recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0025] Embodiments of the present invention propose a new domain-aware-based bias elimination technology to realize unbiased zero-sample image recognition applications. Its core idea is to construct two complementary visual representations, that is, non-semantic visual representation and semantic visual representation to process known domain and unknown domain samples respectively. For non-semantic visual representation, an adaptive second-order embedding module can be designed to extract the second-order statistics in visual information, and the inter-class difference can be maximized through adaptive edge Softmax. This enables semantic-free visual representations to be sufficiently discriminative for both category pre...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an image recognition method, and the method comprises the steps: S1, obtaining a training image set, carrying out the training of each training image in the training image set and a category index corresponding to the training image, and learning and extracting a non-semantic visual expression; S2, aligning each training image in the training image set with the semantic label corresponding to the training image, and learning to extract visual expression of semantic alignment; S3, identifying and analyzing the non-semantic visual expression and the semantic alignment visual expression to obtain a visual prejudice elimination model; and S4, inputting the to-be-identified image into the visual bias elimination model, and identifying the to-be-identified image. Accordingto the image recognition method provided by the invention, the visual bias elimination model is established, so that the perception effect on known domain and unknown domain samples can be improved,and accurate recognition of an unbiased zero sample is further realized.

Description

technical field [0001] The present invention relates to the application of a bias elimination technology based on domain perception to realize the recognition of unbiased zero-sample images, in particular to an image recognition method and device. Background technique [0002] Zero-shot learning aims to recognize image samples of known categories (known domain) or unknown categories (unknown domain) simultaneously. Recent methods focus on learning a semantically aligned visual representation to transfer knowledge from known domains to unknown domains. However, due to the weak discriminative nature of semantic knowledge, it is difficult for this semantically aligned visual representation to separate the two domains. Therefore, images of unknown domains are more likely to be recognized as known domain categories. Contents of the invention [0003] (1) Technical problems to be solved [0004] An image recognition method and device provided by the present invention are used ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06K9/62
CPCG06N3/08G06F18/214
Inventor 张勇东闵少波谢洪涛
Owner UNIV OF SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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