Large-scale remote sensing image content retrieval method based on deep adversarial Hash learning
A remote sensing image, large-scale technology, applied in the direction of still image data retrieval, still image data index, still image data query, etc., to achieve the effect of improving retrieval accuracy, improving retrieval accuracy, and increasing retrieval efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0055] The invention provides a large-scale remote sensing image content retrieval method based on deep adversarial hashing learning, and establishes a remote sensing image library{I 1 ,I 2 ,...,I N}, the category corresponding to the image is {Y 1 ,Y 2 ,...,Y N}; Select 80% samples from each category to build a training sample library {I 1 ,I 2 ,...,I l}; training depth against hashing learning model; using the trained depth against hashing learning model, for the entire library {I 1 ,I 2 ,...,I N} for hash encoding to get the hash database of the image {B 1 ,B 2 ,...,B N}; For the query image I' input by the user, use the trained deep adversarial hash learning model to encode B'; calculate the similarity distance between the query image B' and the hash codes of all images in the hash database, and according to the distance Return the number of images required by the user in ascending order. The invention has the advantages of fast retrieval speed and high retrie...
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