Supercharge Your Innovation With Domain-Expert AI Agents!

Method and device for evaluating robustness of similar image retrieval algorithm

A retrieval algorithm and similar image technology, applied in computing, special data processing applications, instruments, etc.

Active Publication Date: 2017-11-07
诺亚机器人科技(上海)有限公司
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, currently no factors can be identified that affect the robustness of similarity image retrieval algorithms

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
  • Method and device for evaluating robustness of similar image retrieval algorithm
  • Method and device for evaluating robustness of similar image retrieval algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is some embodiments of the present invention, but not all of them. Based on the implementation manners in the present invention, all other implementation manners obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0022] The present invention provides a method for evaluating the robustness of a similar image retrieval algorithm. The method provides a test data set of a specified category, and the test data set includes interference data and at least two sets of test arrays, each set of test arrays includes A preset number of sample...

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 provides a method and device for evaluating robustness of a similar image retrieval algorithm, wherein the method comprises: retrieving in a test data set for each image to be retrieved according to the similar image retrieval algorithm, and setting a corresponding retrieval integral for each image to be retrieved according to the retrieval results; determining a corresponding original average integral to the similar image retrieval algorithm based on the corresponding retrieval integral of each image to be retrieved; reducing quality of each sample in at least two test arrays; retrieving again in the test data set according to the similar image retrieval algorithm so as to obtain a corresponding actual average integral of the similar image retrieval algorithm at the premise of image processing; determining factors affecting the robustness of the similar image retrieval algorithm based on the original average integral and the actual average integral. The method and device according to the technical scheme provided herein enable factors affecting the robustness of the similar image retrieval algorithm to be determined.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of image retrieval, in particular to a robustness evaluation method and device for a similar image retrieval algorithm. Background technique [0002] At present, image recognition technology has been applied to face recognition in the field of security, vehicle retrieval in the field of intelligent transportation, etc. Similar image retrieval algorithms usually include three main functions: feature extraction, feature similarity calculation, and similarity ranking. The algorithm extracts the feature of the image to be retrieved, and calculates the similarity with each feature value in the feature database, so that the picture with the highest similarity can be returned. Ideally, the image with the highest similarity in similarity ranking is the target image. The images to be retrieved obtained in the real scene are affected by external conditions, such as changes in lighting condi...

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): G06F17/30
CPCG06F16/583
Inventor 蒋化冰郝瑞明廖凯齐鹏举方园米万珠舒剑吴琨管伟罗璇
Owner 诺亚机器人科技(上海)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More