Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Corner point detecting and matching-based medicine recognition system and recognition method thereof

A corner detection and recognition method technology, applied in the field of computer vision and machine learning, can solve the problem that corners do not have rotation invariance and scale invariance, to help visual obstacles, high recognition rate and accuracy, and improve corners. Effect of point detection rate

Active Publication Date: 2017-07-25
JIAXING SEC VIEW INFORMATION TECH CO LTD
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Both the FAST and AGAST algorithms can quickly detect and extract the local corner features of the image to meet the real-time processing of the video frame, but because only the grayscale is processed, the corner points do not have rotation invariance and scale invariance

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
  • Corner point detecting and matching-based medicine recognition system and recognition method thereof
  • Corner point detecting and matching-based medicine recognition system and recognition method thereof
  • Corner point detecting and matching-based medicine recognition system and recognition method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The present invention discloses a medicine identification system based on corner detection and matching and a medicine identification method based on corner detection and matching. The specific implementation of the present invention will be further described below in conjunction with preferred embodiments.

[0052] See attached Figure 1 to Figure 4 , The drug identification method based on corner detection and matching includes the following steps:

[0053] Step one (medicine image corner detection): detect the corner features of the drug image according to the adaptive threshold multi-scale AGAST algorithm, and obtain several corner points;

[0054] Step 2 (Description of the corner points of the medicine image): According to the improved FREAK description operator, use the binary feature description string to describe the corner points of the above medicine image;

[0055] Step 3: Repeat steps 1 and 2 to train the drug images and establish a drug library corresponding to 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 corner point detecting and matching-based medicine recognition system and a corner point detecting and matching-based medicine recognition method. According to the adaptive-threshold multi-scale AGAST algorithm, the corner point features of a medicine image are detected, and then a plurality of corner points are obtained. Based on improved FREAK description operators, the corner points of the medicine image are described by utilizing binary feature description character strings. The medicine image is trained, and then a medicine library corresponding to feature descriptors and the medicine information is established. Based on the feature descriptors of a training image and a target image, the hamming distance between the two images is calculated, so that two images are matched. Therefore, corresponding medicines can be recognized. In various complex environments, the system and the method are high in recognition speed and accuracy. Meanwhile, the visually impaired people can be better helped.

Description

Technical field [0001] The invention belongs to the technical field of computer vision and machine learning, and specifically relates to a medicine identification system based on corner detection and matching and a medicine identification method based on corner detection and matching. Background technique [0002] According to incomplete statistics, there are approximately 342 million people suffering from visual impairment worldwide. Visual impairment refers to impaired vision, disability or defect caused by congenital and acquired causes such as aging, eye diseases and eye injuries, which manifests as the part of the visual organs (including eyeballs and eye nerves) and the brain optic nerve center. Or all obstacles, so that the eyesight of the patient is impaired to varying degrees or the field of vision becomes smaller, and the patient cannot correctly identify external things. According to relevant regulations, the visual acuity of visually impaired patients is below 0.3 or...

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
IPC IPC(8): G06K9/20G06K9/62
CPCG06V10/22G06F18/22
Inventor 金捷
Owner JIAXING SEC VIEW INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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