Analysis apparatus, imaging system, and storage medium

• US 11,067,447 B2
• Filed: 04/12/2019
• Issued: 07/20/2021
• Est. Priority Date: 04/23/2018
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Sano, Daisuke
• Primary Examiner(s): Ayub, Hina F
• Application Number:
  US16/382,251
• Publication Number:
  US 20190323889A1
• Time in Patent Office: 830 Days
• CPC Class Codes: G01J 2003/2826 Multispectral imaging, e.g. filter imaging
• CPC Class Codes: G01J 3/28 Investigating the spectrum using colour filters G01J3/51
• CPC Class Codes: G01J 3/2823 Imaging spectrometer
• CPC Class Codes: G01N 21/255 Details, e.g. use of specially adapted sources, lighting or optical systems
• 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 2201/1293 resolving multicomponent spectra

Abstract

An analysis apparatus includes an estimator configured to estimate spectral information of an object based on information acquired by a spectroscope, and a processor configured to tag the spectral information of the object with a feature amount of the object. The estimator performs different estimation processing for each of a plurality of spectroscopes, and the processor performs regression processing common to the plurality of spectroscopes.

Claims

1. An analysis apparatus comprising:

one or more processors configured to execute;

first estimation processing to estimate first spectral information of an object based on first information acquired by a first spectroscope;

second estimation processing to estimate second spectral information of the object based on second information acquired by a second spectroscope;

first regression processing to tag the first spectral information with a feature amount of the object; and

second regression processing to tag the second spectral information with the feature amount,

wherein the first estimation processing and the second estimation processing are different from each other,

wherein first regression processing and the second regression processing are common to each other; and

wherein, in the first and second regression processing, it is determined whether the object is a predetermined object based on the first and second spectral information.

2. The analysis apparatus according to claim 1, wherein the first information and the second information are first and second images of the object.

3. The analysis apparatus according to claim 1, wherein the first spectral information and the second spectral information are first and second spectra of the object.

4. The analysis apparatus according to claim 1, wherein the first spectral information and second spectral information are first and second spectral coefficients of the object.

5. The analysis apparatus according to claim 4, wherein each of the first and second spectral coefficients is a coefficient representing a characteristic of a wavelength of reflection light or transmission light of the object.

6. The analysis apparatus according to claim 4, wherein, in the first and second estimation processing, the first and second spectral coefficients are estimated by performing four arithmetic operations for the first and second information, respectively.

7. The analysis apparatus according to claim 6, wherein each of first and second expressions is used to estimate the first and second spectral coefficients-are tagged by a linear regression.

8. The analysis apparatus according to claim 4, wherein, in the first and second estimation processing, the first and second spectra of the object are estimated based on the first and second spectral coefficients according to a wavelength of reflection light or transmission light of the object, respectively.

9. The analysis apparatus according to claim 4, wherein the spectral coefficient having the highest contribution ratio out of the first and second spectral coefficients has a permissible error of 30% or less.

10. The analysis apparatus according to claim 1, wherein the feature amount is property information of the object.

11. The analysis apparatus according to claim 1, wherein, in the first and second estimation processing, each of the first and second spectral information is estimated based on a variable term obtained by removing a constant term from each of the first and second information.

12. The analysis apparatus according to claim 11, wherein an absolute value of the variable term is smaller than an absolute value of the constant term.

13. An imaging system comprising:

an analysis apparatus; and

a spectroscope configured to acquire information,

wherein the analysis apparatus comprises;

one or more processors configured to execute;

first estimation processing to estimate first spectral information of an object based on first information acquired by a first spectroscope;

second estimation processing to estimate second spectral information of the object based on second information acquired by a second spectroscope;

first regression processing to tag the first spectral information with a feature amount of the object; and

second regression processing to tag the second spectral information with the feature amount,

wherein the first estimation processing and the second estimation processing are different from each other,

wherein first regression processing and the second regression processing are common to each other.

14. A non-transitory computer-readable storage medium storing a program that causes a computer to execute a method that includes:

a first estimation step of estimating first spectral information of an object based on first information acquired by a first spectroscope;

a second estimation step of estimating second spectral information of the object based on second information acquired by a second spectroscope;

a first regression step of tagging the first spectral information with a feature amount of the object; and

a second regression step of tagging the second spectral information with the feature amount,

wherein the first estimation step and the second estimation step are different from each other,

wherein the first regression step and the second regression step are common to each other, and

wherein, in the first and second regression steps, it is determined whether the object is a predetermined object based on the first and second spectral information.