Meat assessment device

Patent metadata

Field	Value
Publication number	US-9546968-B2
Application number	US-201414414679-A
Country	US
Kind code	B2
Filing date	May 2, 2014
Priority date	May 2, 2014
Publication date	Jan 17, 2017
Grant date	Jan 17, 2017

Abstract

A method for assessing the quality of a piece of meat may be described. The method may include creating a plurality of cross-sectional images through a piece of meat. The method may additionally include performing image analysis on at least one of the images to determine the arrangement of fat and lean meat within the piece of meat. The arrangement may be indicative of the quality of the piece of meat.

First claim

What is claimed is:

1. A method to assess a quality of a piece of meat, the method comprising:
creating a cross-sectional image through the piece of meat;
receiving a selected area of the cross-sectional image:
performing a texture analysis on the selected area of the cross-sectional image to determine a texture of the selected area, wherein the texture of the selected area includes a variation in a coloring associated with the cross-sectional image and a variation in an intensity associated with the cross-sectional image: and
performing an image analysis on the selected area of the cross-sectional image to determine an arrangement of fat meat and lean meat within the piece of meat, wherein the arrangement of fat meat and lean meat within the piece of meat is indicative of the quality of the piece of meat.

2. The method of claim 1 , further comprising:
creating additional sequential cross-sectional images through the piece of meat, wherein the additional sequential cross-sectional images are tomographic images created using an x-ray computer tomography scanner: and
combining the cross-sectional image and the additional sequential cross-sectional images to produce a three-dimensional representation of the piece of meat.

3. The method of claim 2 , further comprising:
determining a cutting pattern for the piece of meat in dependence on the arrangement of fat meat and lean meat within the piece of meat.

4. The method of claim 1 , wherein the texture analysis is performed using a Gray-Level Co-Occurrence Matrix (GLCM) algorithm.

5. The method of claim 1 , wherein the piece of meat is at least a section of an animal body.

6. The method of claim 1 , wherein the piece of meat is at least a section of an animal carcass.

7. A method to value a piece of meat, the method comprising:
creating a cross-sectional image through the piece of meat;
receiving a selected area of the cross-sectional image;
performing a texture analysis on the selected area of the cross-sectional image to determine a texture of the selected area, wherein the texture of the selected area includes a variation in a coloring associated with the cross-sectional image and a variation in an intensity associated with the cross-sectional image: and
performing an image analysis on the selected area of the cross-sectional image to determine an arrangement of fat meat and lean meat within the piece of meat, wherein the arrangement of fat meat and lean meat within the piece of meat is indicative of a quality of the piece of meat.

8. A meat quality assessment apparatus, the meat quality assessment apparatus comprising:
a scanner adapted to:
produce a cross-sectional image through a piece of meat;
select an area of the cross-sectional image;
perform a texture analysis on the selected area of the cross-sectional image to determine a texture of the selected area, wherein the texture of the selected area includes a variation in a coloring associated with the cross-sectional image and a variation in an intensity associated with the cross-sectional image; and

a processor adapted to:
perform an image analysis on the selected area of the cross-sectional image to determine an arrangement of fat meat and lean meat within the piece of meat, wherein the arrangement of fat meat and lean meat within the piece of meat is indicative of the quality of the piece of meat.

9. The meat quality assessment apparatus of claim 8 , wherein the scanner is further configured to:
produce additional sequential cross-sectional images through the piece of meat wherein the additional sequential cross-sectional images are tomographic images created using an x-ray computer tomography scanner.

10. The meat quality assessment apparatus of claim 9 , wherein the processor is further configured to:
combine the additional sequential cross-sectional images and the cross-sectional image to produce a three-dimensional representation of the piece of meat.

11. The meat quality assessment apparatus of claim 10 , wherein the processor is further configured to:
determine a cutting pattern for the piece of meat in dependence on an arrangement of fat meat and lean meat within the piece of meat.

12. The meat quality assessment apparatus of claim 8 , wherein the meat quality assessment apparatus further comprises:
a selection means configured to: select another area of the cross-sectional image for analysis; and
wherein the processor is further configured to:
perform another texture analysis on the other selected area, wherein the other texture analysis is performed using a Gray-Level Co-Occurrence Matrix (GLCM) algorithm.

13. The meat quality assessment apparatus of claim 8 , wherein the piece of meat is at least a section of an animal body.

14. The meat quality assessment apparatus of claim 8 , wherein the piece of meat is at least a section of an animal carcass.

15. The method of claim 4 , further comprising:
determining at least one of a GLCM correlation value and a GLCM dissimilarity value from the GLCM algorithm, wherein the at least one of the GLCM correlation value and the GLCM dissimilarity value is indicative of a degree of marbling.

16. The meat quality assessment apparatus of claim 12 , wherein the processor is further configured to:
determine at least one of a GLCM correlation value and a GLCM dissimilarity value from the GLCM algorithm, wherein the at least one of the Gray-Level Co-Occurrence Matrix (GLCM) correlation value and the Gray-Level Co-Occurrence Matrix (GLCM) dissimilarity value is indicative of a degree of marbling.

Assignees

• Empire Technology Dev Llc

Inventors

• Cooke Cameron

Classifications

• G06T7/0004

  Industrial image inspection · CPC title

• G01N33/12

  Meat; Fish · CPC title

• G06T2207/30128

  Food products · CPC title

• G06T15/00

  Three-dimensional [3D] image rendering · CPC title

• G06T2207/20021

  Dividing image into blocks, subimages or windows · CPC title