Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-feature picture recognition method and device, and computer-readable storage medium

A picture recognition and multi-feature technology, applied in the field of image recognition, can solve the problems of low picture recognition effect and inability to effectively integrate multi-features, etc., to achieve the effect of recognition accuracy

Inactive Publication Date: 2018-07-31
SHENZHEN UNIV
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide a multi-feature picture recognition method, aiming to solve the technical problem of low picture recognition effect caused by the inability to effectively fuse multiple features when merging picture features in the prior art

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
  • Multi-feature picture recognition method and device, and computer-readable storage medium
  • Multi-feature picture recognition method and device, and computer-readable storage medium
  • Multi-feature picture recognition method and device, and computer-readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0031] The main solution of the embodiment of the present invention is: obtain the picture to be recognized, and process the picture to be recognized according to the pre-built multi-feature joint dictionary model; The label category of the picture to be recognized; outputting the confirmed label type of the picture to be recognized.

[0032] Due to the fact that in the prior art, multi-feature fusion cannot be effectively used when fusing image features, resulting in the problem that the accuracy of image recognition is too low.

[0033] The present invention provides a solution, by constructing the dictionary structure of the feature joint dictionary model, determining the label type of the image to be recognized and searching the relevant image data in the database based on the label category, so as to achieve the ...

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 discloses a multi-feature picture recognition method which comprises: acquiring a picture to be recognized, processing the picture to be recognized according to a pre-built multi-featurejoint dictionary model; and determining a tag category of the picture to be recognized according to a processed result of the picture to be recognized by the multi-feature joint dictionary module; and outputting the confirmed tag category of the picture to be recognized. The invention also discloses a multi-feature picture recognition device and a computer-readable storage medium. The method constructs the multi-feature joint dictionary model, calculates information of the tag category of the picture to be identified, and searches for related picture information through the tag category, thereby realizing a beneficial effect of improving the accuracy of multi-feature picture recognition.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a multi-feature image recognition method, device and computer-readable storage medium. Background technique [0002] There is a widely accepted fact in modern image recognition technology: multiple feature descriptions can provide more information about the surrounding world. For example, compared to RGB data, which can capture appearance and texture information, RGB-D data can additionally provide distance information and be robust to illumination differences; several cameras can capture the same object from different angles, which will reduce false information. dependency. Scenarios like these place enormous demands on analytics algorithms. [0003] With the efforts of recent researchers, the academic community has proposed many effective and efficient methods to explore how to fuse multiple features. Methods for fusing different features can be divided int...

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): G06K9/62
CPCG06F18/28G06F18/24G06F18/253
Inventor 朱英王强昌杨猛
Owner SHENZHEN UNIV