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

Chinese mitten crab uniqueness recognition method based on image matching

A technology of Chinese mitten crab and identification method, which is applied in the field of unique identification of Chinese mitten crab based on image matching, can solve the problem that the uniqueness of Chinese mitten crab cannot be effectively identified.

Active Publication Date: 2018-09-07
安徽工大信息技术有限公司
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0022] The purpose of this patent is to overcome the problem that the uniqueness of Eriocheir sinensis cannot be effectively identified in the existing inspection methods, and provides a unique identification method for Eriocheir sinensis based on image matching. Features such as depressions, protrusions, and textures are analyzed and processed by image analysis, and then compared with the existing image database, the uniqueness of Chinese mitten crabs can be judged based on the similarity

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
  • Chinese mitten crab uniqueness recognition method based on image matching
  • Chinese mitten crab uniqueness recognition method based on image matching
  • Chinese mitten crab uniqueness recognition method based on image matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0112] Such as figure 1 , figure 2 , image 3 , Figure 4 and Figure 5 Shown, a kind of Chinese mitten crab unique identification method based on image matching of the present invention comprises the following steps:

[0113] Step 1: collect the original image A of Chinese mitten crab, and then segment the back image M of Chinese mitten crab;

[0114] Step (1): Remove the background image to obtain the background graphic segmentation map of the Chinese mitten crab ⑤;

[0115] Step Ⅰ: Take the original image A of the back of the Chinese mitten crab, and the shooting tool is a shooting terminal with a camera;

[0116] Step Ⅱ: Convert the collected original image A of Eriocheir sinensis into a grayscale image ①;

[0117] Step Ⅲ: Use Gaussian filtering to denoise the grayscale image ① to obtain the Gaussian filtering image ②;

[0118] Step Ⅳ: Use the sobel operator to detect the edge of the Gaussian filter image ②, and obtain the sobel operator detection image ③;

[0119...

Embodiment 2

[0184] Such as figure 1 , figure 2 , image 3 , Figure 4 and Figure 5 As shown, this embodiment is basically the same as Embodiment 1. Preferably, the total number of matching pairs in this embodiment is 57, the number of correct matching pairs is 52, and the similarity is 91.2281%, so it can be judged Figure 5 The two Chinese mitten crabs are the same one.

[0185] This implementation applies the accelerated robust feature algorithm and the fast approximate nearest neighbor search algorithm to the algorithm, and at the same time combines the feature point mismatch judgment detection to realize the unique identification algorithm of Chinese mitten crab. When the image has the influence of rotation, translation and noise, etc., The present invention has good robustness, significantly improves the accuracy rate of Chinese mitten crab image matching, and ensures the reliable effect of the unique identification of Chinese mitten crab; in addition, according to the experime...

Embodiment 3

[0187] Such as figure 1 , figure 2 , image 3 , Figure 4 and Figure 6 As shown, this embodiment is basically the same as Embodiment 1. Preferably, the total number of matching pairs in this embodiment is 20, the number of correct matching pairs is 0, and the similarity is 0, so it can be judged Figure 6 The two Chinese mitten crabs in are not the same one.

[0188] This implementation applies the accelerated robust feature algorithm and the fast approximate nearest neighbor search algorithm to the algorithm, and at the same time combines the feature point mismatch judgment detection to realize the unique identification algorithm of Chinese mitten crab. When the image has the influence of rotation, translation and noise, etc., The present invention has good robustness, significantly improves the accuracy rate of Chinese mitten crab image matching, and ensures the reliable effect of the unique identification of Chinese mitten crab; in addition, according to the experimen...

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 Chinese mitten crab uniqueness recognition method based on image matching, and belongs to the field of digital image processing. The method comprises the following steps of 1, acquiring the original image A of a Chinese mitten crab, and then segmenting the back image M of the Chinese mitten crab; 2, extracting the feature points of the back image M of the Chinese mitten crab; 3, extracting, from a database, a saved back image Q and feature points of the Chinese mitten crab, matching the feature points of the image Q and the image M; 4, detecting mismatched feature points; 5, calculating the similarity of the image Q and the image M; and 6, ending the matching and outputting crab matching information. The object of the invention is to overcome the problem that theuniqueness of the Chinese mitten crab cannot be effectively recognized in an existing detection method, and determine the uniqueness of the Chinese mitten crab based on similarity by analyzing the images of various recesses, protrusions and textures widely distributed on the crab carapace, and then comparing the images with images saved in a database.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image matching algorithm, in particular to a method for uniquely identifying Chinese mitten crabs based on image matching. Background technique [0002] Chinese velvet crab, also known as river crab, hairy crab or crab, is delicious and nutritious, and is one of the traditional valuable aquatic products in my country. In recent years, the Chinese mitten crab consumer market, represented by Yangcheng Lake hairy crabs, is very hot every autumn and winter, and geographical indication protected products or trademarks named after waters are emerging. However, driven by interests, counterfeit products have been repeatedly banned in the market, especially the phenomenon of counterfeit origin is particularly serious. In order to prevent products from being counterfeited, various anti-counterfeiting measures have been taken in various places. The common anti-counterfeiting met...

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): G06K9/00G06K9/46G06K9/62G06T5/00G06T7/11G06T7/13G06T7/155G06T7/194
CPCG06T7/11G06T7/13G06T7/155G06T7/194G06T2207/20024G06T2207/10004G06V40/40G06V40/10G06V10/446G06V10/757G06F18/22G06T5/70
Inventor 邰伟鹏李浩汪杰张炳良王小林
Owner 安徽工大信息技术有限公司
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