Image retrieval method and system based on global and local feature rearrangement
A technology of local features and global features, applied in the fields of image retrieval and information technology, can solve the problems of low average retrieval accuracy, unlearnability, and inability to express the spatial position information of vehicle components, and achieve the effect of improving the rearrangement effect.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0031] The present invention will be described in further detail below through specific embodiments and accompanying drawings.
[0032] An image retrieval method based on global and local feature rearrangement according to an embodiment of the present invention, used for vehicle image retrieval, includes the following steps:
[0033] (1) Data preparation: Based on the license plate recognition system, the vehicle pictures captured by different cameras are sorted out under each license plate number, and then the vehicle image data set is divided into training set, verification set and retrieval test set according to the ratio of 8:1:1 , randomly select a batch of pictures from each license plate number in the retrieval test set as the query image, and the rest of the pictures are used as the image database.
[0034] (2) Build a distributed deep learning vehicle image retrieval environment based on Pytorch.
[0035] (3) Data preprocessing: normalize the vehicle image data set i...
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