SYSTEM AND METHOD FOR ANALYZING MATERIAL PROPERTIES USING HYPERSPECTRAL IMAGING

• US 20080199080A1
• Filed: 02/21/2008
• Published: 08/21/2008
• Est. Priority Date: 02/21/2007
• Status: Active Grant

• Current Assignee: Carne Tender LLC
• Original Assignee: Board of Regents of the University of Nebraska
• Inventors: SUBBIAH, JEYAMKONDAN, CALKINS, CHRIS RICHARD, SAMAL, ASHOK
• Granted Patent: US 8,280,144 B2
• Time in Patent Office: Days
• US Class Current: 382/190
• CPC Class Codes: G01N 21/31 Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry G01N21/72 takes precedence
• CPC Class Codes: G01N 21/49 within a body or fluid
• CPC Class Codes: G01N 2201/129 Using chemometrical methods
• CPC Class Codes: G01N 33/12 Meat; fish

Abstract

Systems and methods are provided for analyzing material properties of an object using hyperspectral imaging. An exemplary method includes obtaining a hyperspectral image of an object; analyzing the hyperspectral image according to an algorithm; and correlating data obtained from the analysis with material properties of the object.

Claims

1. A system for using hyperspectral imaging to determine material properties of an object, the system comprising:

an imaging component for obtaining a hyperspectral image of at least a portion of an object, said imaging component comprising at least one of a concentrated lighting system and a diffuse lighting system, the diffuse lighting system having a plurality of lamps, a photodiode and a controller;

an analysis component for analyzing said hyperspectral image to generate data that describes material properties of said object; and

an output component for outputting said data.

2. The system of claim 1, wherein said imaging component further comprises:

a hyperspectral camera, wherein said camera comprises a charged-coupled-device camera and a spectrograph;

a scanning component, wherein said scanning component comprises a linear slide; and

a controlling computer for synchronizing the operation of said hyperspectral camera with the operation of said scanning component.

3. The system of claim 1, wherein said photodiode is configured in a feedback loop with said controller.

4. The system of claim 1, wherein said imaging component comprises a sensor and a light source being configured for obtaining hyperspectral images by performing at least one of a diffuse reflectance process and a scattering spectroscopy.

5. The system of claim 1, wherein said imaging component comprises a sensor and a light source being configured for obtaining hyperspectral images by performing at least one of a transmission process and a fluorescence spectroscopy.

6. The system of claim 1, wherein the output component comprises a labeling component that attaches a label to said object, said label having information indicating at least a portion of said data.

7. A method for determining material properties of an object using hyperspectral imaging, comprising:

obtaining a hyperspectral image of at least a portion of an object, said hyperspectral image comprising a plurality of pixels, wherein each of the plurality of pixels comprises a plurality of spectral bands;

removing redundant information to create a simplified image, wherein said removing redundant information comprises performing at least one of a principal component analysis and a partial least squares analysis;

extracting one or more image-textural features from the simplified image; and

correlating said image-textural features with material properties of said object, wherein said correlating comprises applying a pattern-recognition algorithm to said textural features.

8. The method of claim 7, wherein said object comprises a cut of meat.

9. The method of claim 7, wherein said object comprises a tissue sample.

10. The method of claim 7, wherein the hyperspectral image comprises image data obtained from a hyperspectral imaging apparatus, the hyperspectral imaging apparatus comprising a charged-coupled-device camera and a spectrograph.

11. The method of claim 10, wherein said hyperspectral imaging apparatus has a spectral range of 200-2500 nanometers.

12. The method of claim 10, wherein said hyperspectral imaging apparatus has a spectral range of 8,000-12,000 nanometers.

13. The method of claim 7, wherein extracting one or more image-textural features is achieved by performing at least one of a co-occurrence matrix analysis algorithm, a wavelet analysis algorithm, and an analysis utilizing Gabor filters.

14. The method of claim 7, wherein said pattern-recognition algorithm comprises at least one of a discriminant analysis algorithm, a fuzzy modeling algorithm, and a neural network algorithm.

15. A method for predicting a cooked-beef tenderness grade by analyzing a corresponding fresh cut of beef using hyperspectral imaging, the method comprising:

obtaining hyperspectral image data relating to at least a portion of a cut of beef, the hyperspectral image comprising a plurality of lean pixels and a plurality of fat pixels, wherein each of the lean pixels and fat pixels comprises a plurality of spectral bands;

selecting a region of interest, wherein the region of interest comprises at least a portion of the hyperspectral image data;

reducing the spectral dimensionality by performing at least one of a principal component analysis and a partial least squares analysis over the region of interest;

extracting one or more image-textural features by performing at least one of a co-occurrence matrix analysis, a wavelet analysis, and an analysis utilizing Gabor filters; and

applying at least one pattern-recognition algorithm to the image-textural features to determine a tenderness grade for the cut of beef.

16. The method of claim 15, wherein said hyperspectral image data is obtained using a scattering technique.

17. The method of claim 15, wherein said hyperspectral image data is obtained using a technique comprising fluorescence spectroscopy.

18. The method of claim 15, wherein said hyperspectral image data is obtained using a spectroscopy technique comprising transmission.

19. The method of claim 15, wherein said image-textural features comprise one or more of a mean, a variance, a homogeneity, a contrast, a dissimilarity, an entropy, a second moment, and a correlation.

20. The method of claim 15, wherein said tenderness grade comprises one of a set of categories defined with reference to slice shear force values corresponding to cooked cuts of beef.