INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, COMPUTER-READABLE RECORDING MEDIUM, AND INSPECTION SYSTEM

• US 20170154234A1
• Filed: 11/30/2016
• Published: 06/01/2017
• Est. Priority Date: 12/01/2015
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ryosuke Kasahara, Takuya Tanaka
• Inventors: TANAKA, Takuya, KASAHARA, Ryosuke
• Granted Patent: US 10,043,090 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/2433 Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20092 Interactive image processing based on input by user
• CPC Class Codes: G06T 2207/30108 Industrial image inspection
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/454 Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 2201/07 Target detection

Abstract

An information processing device inspects a target image that contains an image of an inspection target. The information processing device includes a pre-processor, a first calculator, a second calculator, and a determiner. The pre-processor is configured to perform pre-processing for comparing the target image with a reference image or a plurality of reference images. The first calculator is configured to define, in the target image, a region of interest (ROI) and surrounding regions that are adjacent to the ROI, and calculate a feature value of the ROI. The second calculator is configured to calculate an outlier from comparison with feature values of images corresponding to the ROI and the surrounding regions in the reference images. The outlier numerically indicates singularity of an image at the ROI. The determiner is configured to provide, based on the outlier, an indicator to be used for the inspection.

Claims

1. An information processing device for inspecting a target image that contains an image of an inspection target, the information processing device comprising:

a pre-processor configured to perform pre-processing for comparing the target image with a reference image or a plurality of reference images;

a first calculator configured to define, in the target image, a region of interest (ROI) and surrounding regions that are adjacent to the ROI, and calculate a feature value of the ROI;

a second calculator configured to calculate an outlier from comparison with feature values of images corresponding to the ROI and the surrounding regions in the reference images, the outlier numerically indicating singularity of an image at the ROI; and

a determiner configured to provide, based on the outlier, an indicator to be used for the inspection.

2. The information processing device according to claim 1, further comprising a third calculator configured to reduce noise components included in the outlier when the outlier is obtained, wherein

the determiner generates the indicator by using the outlier from which the noise components have been cut out.

3. The information processing device according to claim 1, wherein the feature value is a value generated by use of a luminance value, a color value, edge information, spatial frequency information, texture information, or a neural network.

4. The information processing device according to claim 1, further comprising a fourth calculator configured to quantify the singularity of the image in the form of a standard score with respect to corresponding regions in the reference images.

5. The information processing device according to claim 1, further comprising an interface configured to enable change of a size of the surrounding regions.

6. The information processing device according to claim 1, further comprising an interface configured to enlarge or reduce the entire target image or a part of the target image in size.

7. The information processing device according to claim 1, wherein the second calculator configured to calculate the outlier by using the target image that has been enlarged or reduced in size.

8. The information processing device according to claim 1, further comprising:

an interface configured to enable addition of the reference image; and

a fifth calculator configured to enable a threshold for the outlier to be externally set, wherein

the second calculator updates parameters for use in calculating the outlier while including the added reference image in the calculation, and calculates the outlier with the updated parameters after the updating.

9. A method performed in an information processing device to quantify a target image that contains an image of an inspection target, the method comprising:

performing pre-processing for comparing the target image with a reference image or a plurality of reference images;

defining, in the target image, a region of interest (ROI) and surrounding regions that are adjacent to the ROI to calculate a feature value of the ROI;

calculating an outlier from comparison with feature values of images corresponding to the ROI and the surrounding regions in the reference images, the outlier numerically indicating singularity of an image at the ROI; and

providing, based on the outlier, an indicator to be used for the inspection.

10. The method according to claim 9, further comprising:

reducing noise components included in the outlier when the outlier is obtained; and

generating the indicator by using the outlier from which the noise components have been cut out.

11. The method according to claim 9, wherein the feature value is a value generated by use of a luminance value, a color value, edge information, spatial frequency information, texture information, or a neural network.

12. The method according to claim 9, further comprising quantifying the singularity of the image in the form of a standard score with respect to corresponding regions in the reference images.

13. A non-transitory computer-readable recording medium with an executable program stored thereon, wherein the program instructs a computer to perform the method according to claim 9.

14. An inspection system for inspecting an inspection target, the inspection system comprising:

an image capturing unit configured to acquire a target image that contains an image of the inspection target;

a pre-processor configured to perform pre-processing for comparing the target image with a reference image or a plurality of reference images;

a first calculator configured to define, in the target image, a region of interest (ROI) and surrounding regions that are adjacent to the ROI, and calculate a feature value of the ROI;

a second calculator configured to calculate an outlier from comparison with feature values of images, in the reference images, that correspond to the ROI and the surrounding regions, the outlier numerically indicating the singularity of an image at the ROI;

a determiner configured to provide, based on the outlier, an indicator to be used for the inspection; and

a third calculator configured to reduce noise components included in the outlier when the outlier is obtained, wherein

the determiner provides the indicator by using the outlier from which the noise components have been cut out, and determines defection in the inspection target from the target image by using the indicator.