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

Individual pig identification method based on Gabor direction histograms and pig body hair modes

A technology of direction histogram and recognition method, which is applied in character and pattern recognition, image enhancement, image analysis, etc., and can solve difficult problems

Active Publication Date: 2017-12-05
JIANGSU UNIV
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the most difficult and critical problem is the identification of individual pigs in the process of movement. At present, the widely used method is ear tag RFID. There are few relevant literature reports on the use of machine vision technology to identify individual pigs in large-scale pig farms.

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
  • Individual pig identification method based on Gabor direction histograms and pig body hair modes
  • Individual pig identification method based on Gabor direction histograms and pig body hair modes
  • Individual pig identification method based on Gabor direction histograms and pig body hair modes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Combine below figure 1 Pig individual identification flow chart and figure 2 The process diagram of sample creation further explains the specific implementation of each part involved. figure 1 Among them, the purpose of image preprocessing is to enhance the picture quality and completely extract individual pig targets, and the second is to find stable feature areas and prepare for the subsequent hair pattern feature extraction; feature extraction includes Gabor filter filtering, hair Calculation of mode direction field and calculation of Gabor direction histogram; target recognition includes chi-square distance calculation and target matching. figure 2 It is a process diagram of sample establishment of the present invention, which mainly introduces the establishment process of the sample library of the present invention.

[0028] Step 1: Collect video sequences of pigs raised in groups under the state of looking down, select appropriate sample frames from the collec...

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 an individual pig identification method based on Gabor direction histograms and pig body hair modes. According to the method, firstly, a target extraction method based on adaptive segmentation and multi-threshold segmentation is utilized to extract multiple pig targets of each picture; secondly, after the complete pig targets are extracted, a pig body key point detection algorithm is utilized to extract stable characteristic areas from pig profiles, and grid division of the stable characteristic areas is further carried out; thirdly, a Gabor filter is utilized in each grid of the selected stable characteristic areas to calculate a hair mode direction field, and the direction field information is utilized in each grid to calculate the Gabor direction histograms; and lastly, chi-square distance is utilized to measure difference between the different Gabor direction histograms, matching with pigs in a database is further carried out, and the purpose of pig individual identity identification is realized. The method is advantaged in that a new way is provided for no-stress pig individual identification, and certain technical support is provided for individual behavior analysis of the pigs bred in groups.

Description

technical field [0001] The invention relates to machine vision technology and pattern recognition technology, in particular to a pig individual recognition method in a surveillance video of group pig raising under a bird's-eye view state. Background technique [0002] With the development of large-scale pig farming and computer technology, the analysis of individual pig behavior in video sequences of group pig raising based on machine vision has attracted more and more attention from scholars at home and abroad. Among them, the most difficult and critical problem is the identification of individual pigs in the process of movement. At present, the widely used method is ear tag RFID. There are few relevant literature reports on the use of machine vision technology to identify individual pigs in large-scale pig farms. The invention provides an individual identification method for group-raised pigs based on the Gabor direction histogram and hair pattern characteristics, which la...

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): G06K9/00G06K9/46G06K9/62G06T5/40G06T7/10
CPCG06T5/40G06T7/10G06V20/52G06V10/44G06F18/241
Inventor 朱伟兴赵伟李新城
Owner JIANGSU UNIV
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