Image processing method used for segmenting and grading beef musculi oculi marbling

A marble pattern and image processing technology, applied in image data processing, image analysis, character and pattern recognition, etc., can solve the problems of high rating cost, low efficiency, and inconsistency in the subjectivity of manual rating methods, and achieve high rating cost , solve the subjectivity and inconsistency, the effect of good market application prospects

Inactive Publication Date: 2018-01-16
王虎峰 +1
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention solves the problems of subjectivity and inconsistency, high cost and low efficiency of the manual rating method

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
  • Image processing method used for segmenting and grading beef musculi oculi marbling
  • Image processing method used for segmenting and grading beef musculi oculi marbling
  • Image processing method used for segmenting and grading beef musculi oculi marbling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] This embodiment describes the specific steps in detail.

[0051] (1) Image segmentation of beef eye muscle section

[0052] Specifically include the following steps:

[0053] 1. Carry out image gray-value conversion to the color image of beef eye muscle cut surface obtained by digital camera, and obtain the gray-scale image of eye muscle cut surface (such as figure 2 ).

[0054] 2. Utilize the Otsu method (Otsu) to process the grayscale image of the eye muscle section to obtain a binary image of the eye muscle section (such as image 3 ).

[0055] 3. Marking connected regions on the binary image of the eye muscle section.

[0056] 4. Find the connected area mark corresponding to the central point area of ​​the grayscale image of the eye muscle section, set the corresponding grayscale image pixels of the eye muscle section under this marked area as the foreground, and clear all the pixels in the other marked areas As the background, get the initial area image of th...

Embodiment 2

[0112] Repeat steps (1) and (2) in Example 1 for 18 sample images with typical beef marbling grades to obtain the beef marbling grade (MB) and eye muscle fat ratio (P) of 18 groups of sample images , eye muscle large fat block ratio (Q), box counting dimension (Db), and information dimension (Di) corresponding relationship data, as shown in Table 1:

[0113] Table 1 Correspondence data of MB, P, Q, Db, Di of 18 groups of sample images

[0114]

[0115]

[0116] According to the corresponding relationship data between the marbling grade (MB) of the sample image and the proportion of eye muscle fat (P), the proportion of eye muscle large fat mass (Q), and the box dimension (Db), the following equations can be established:

[0117]

[0118] Determination of regression coefficient β by least square method 0 , β 1 , β 2 , β 3 . Finally, the multiple linear regression equation of beef marbling grade was established as follows:

[0119] MB=5.820P+12.496Q-0.385Db+0.0527...

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 present invention provides an image processing method used for segmenting and grading a beef musculi oculi marbling. The image processing method provided by the present invention concretely comprises the steps of segmenting a cattle carcass musculi oculi section image; extracting the marbling in a beef musculi oculi area; and grading the beef musculi oculi marbling. The image processing methodof the present invention is a method of automatically segmenting the beef musculi oculi, extracting the marbling in the musculi oculi and grading the marbling objectively and efficiently based on thecomputer vision and image processing technologies, by grading the quality of the beef automatically, solves the problems that a conventional artificial grading method has the subjectivity and the inconsistency, the grading cost is high, the efficiency is low, etc., is suitable for but not limited to the beef production enterprises and the quality detection departments, and has the good market application prospect.

Description

technical field [0001] The invention relates to a technology based on computer vision and image processing, in particular to an image processing method for segmenting and grading beef eye muscle marbling. Background technique [0002] Beef marbling is an important indicator of beef grade evaluation. At present, the beef grading methods in various countries in the world generally adopt subjective artificial visual evaluation. Beef grading staff can evaluate the marbling grade of beef by observing the richness of intramuscular fat (marbling) at the cross-section of the longissimus dorsi (eye muscle) of the 12th to 13th or 6th to 7th intercostal intercostal muscles (eye muscles) of the beef carcass, and then Refer to the muscle color, fat color and physiological maturity of beef to finally evaluate the beef quality grade. The advantage of the manual visual grading method is that the grader's intuition and experience can ensure high beef grading accuracy, and the grading proce...

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): G06T7/00G06T7/12G06T7/194G06K9/62G06F17/12
Inventor 王虎峰逄滨
Owner 王虎峰
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products