Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Fine-grained image retrieval method and system

An image retrieval, fine-grained technology, applied in still image data retrieval, still image data indexing, digital data information retrieval, etc., can solve the problems of increasing fine-grained image recognition time, large intra-class differences, and small inter-class differences, etc. Achieve the effect of shortening retrieval time, efficient storage, and improving time efficiency

Active Publication Date: 2021-06-29
NANJING UNIV OF SCI & TECH
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, this feature of small inter-class differences and large intra-class differences increases the complexity of deep networks, which in turn increases the recognition time of fine-grained images.

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
  • Fine-grained image retrieval method and system
  • Fine-grained image retrieval method and system
  • Fine-grained image retrieval method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] See figure 1 , this embodiment is used to provide a fine-grained image retrieval method, the retrieval method includes the following steps:

[0026] S1: Calculate the hash code of the image to be retrieved;

[0027] S2: Calculate the Hamming distance between the hash code of the picture to be retrieved and the hash code of each picture in the database, and sequentially select a predetermined number of the pictures according to the order of the Hamming distance from small to large as a retrieval image.

[0028] For retrieval technology, it is necessary to be able to quickly retrieve fine-grained images. The hash representation can map data from a high-dimensional space to a low-dimensional space, and use binary codes (hash codes) to represent the data, and the similarity between data can be determined by the Hamming distance between the hash codes. express. This short binary code can be stored efficiently, and then the time efficiency of retrieval can be improved by ...

Embodiment 2

[0109] See Figure 7 , this embodiment is used to provide a fine-grained image retrieval system, and the retrieval system includes:

[0110] The hash code calculation unit M1 is used to calculate the hash code of the picture to be retrieved;

[0111] The retrieval picture selection unit M2 is used to calculate the Hamming distance between the hash code of the picture to be retrieved and the hash code of each picture in the database, and sequentially select predetermined The number of the pictures is used as the retrieval picture, that is, the picture with a small Hamming distance is preferentially selected as the retrieved retrieval picture.

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 relates to a fine-grained image retrieval method and system, and the method comprises the steps: firstly calculating the Hash code of a to-be-retrieved image, then calculating the Hamming distance between the Hash code of the to-be-retrieved image and the Hash code of each image in a database, and sequentially selecting a predetermined number of images as retrieval images according to the order of the Hamming distances from small to large, wherein the Hash code is a short binary code and can be efficiently stored in the database, so that the similarity between the data is represented by calculating the Hamming distance, the retrieval time of the fine-grained image can be shortened, and the retrieval time efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of fine-grained image retrieval, in particular to a fine-grained image retrieval method and system. Background technique [0002] Image retrieval technology is one of the core issues in the field of computer vision. Image retrieval means that given a picture, it is necessary to retrieve pictures similar to the picture in the database. In the image retrieval technology, most of the current work is researched on the basis of general images, and the fine-grained image retrieval technology still needs to be explored. Fine-grained images refer to the subdivision of images belonging to a certain basic category, such as subdividing various birds. Compared with general-purpose images, each subcategory of fine-grained images belongs to the same category, so the overall structure of different subcategories is very similar, and due to shooting angles or poses, images belonging to the same subcategory There will also ...

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): G06F16/51G06F16/583G06N3/04
CPCG06F16/51G06F16/583G06N3/045
Inventor 项欣光张亚杰金露
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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