Depth feature comparison weighted image retrieval method based on vector comparison strategy
A deep feature and image retrieval technology, applied in the field of deep feature contrast weighted image retrieval based on vector contrast strategy, to achieve the effect of improving accuracy and enhancing advanced semantic features
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0058] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific examples.
[0059] The basic idea of the present invention is: an image is input into a deep convolutional neural network model to generate deep features, the deep features include a set of feature maps, each feature map represents the local semantic information of the image, and the human visual system can select and distinguish The key semantic information of the image. Starting from the basic idea, a deep feature comparison weighted image retrieval method based on a vector comparison strategy proposed by the present invention, through image depth feature comparison, assigns higher weights to those feature maps that include key semantic information through weight values, so as to Improve the discriminability of images.
[0060] A deep feature contrast weighted image retrieval me...
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