Large-scale image data similarity searching method based on EMD (earth mover's distance)
An EMD distance and similarity search technology, applied in electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as large workload of manual annotation, unfavorable computing load of computing nodes, and unsatisfactory scalability performance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0061] Such as image 3 As shown, the steps of the large-scale image data similarity search method based on the EMD distance of this embodiment include:
[0062] 1) An image data mapping function f designed to map image data to a one-dimensional real key value space Ω(Φ). The image data mapping function f includes image data and one of the keys in the one-dimensional real key value space Ω(Φ). Mapping relationship between;
[0063] 2) Start a MapReduce job MR1, and use the MapReduce job MR1 to estimate the query processing load corresponding to each key value in the one-dimensional real key value space Ω(Φ) based on the query image set Q and the image set I to be retrieved;
[0064] 3) Start a MapReduce job MR2, and use the Map task of MapReduce job MR2 to cut the one-dimensional real key value space Ω(Φ) based on the query processing load estimated in step 2), and divide the one-dimensional real key value space Ω( Φ) The image data fragments in the query image set Q corresponding t...
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