INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM

• US 20160267647A1
• Filed: 03/08/2016
• Published: 09/15/2016
• Est. Priority Date: 03/10/2015
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Higo, Tomoaki
• Granted Patent: US 10,157,456 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10152 Varying illumination
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/0004 Industrial image inspection

Abstract

An information processing apparatus for, to classify and detect a plurality of types of defects, detecting a defect in a target object without using data obtained by prior learning includes an acquisition unit configured to acquire an image group obtained by capturing a target object irradiated with light from a plurality of illumination units placed at a plurality of different positions, a generation unit configured to, based on luminance information of images included in the image group, generate a first luminance profile indicating a change in a luminance value of a first region, which is a region corresponding between the images, and a second luminance profile indicating a change in a luminance value of a second region, which is a region corresponding between the images, and a detection unit configured to detect a defect in the target object based on the first luminance profile and the second luminance profile.

Claims

1. An information processing apparatus for detecting a defect in a target object without using data obtained by prior learning, the information processing apparatus comprising:

an acquisition unit configured to acquire an image group obtained by imaging a target object irradiated with light from a plurality of illumination units placed at a plurality of different positions;

a generation unit configured to, based on luminance information of images included in the image group, generate a first luminance profile indicating a change in a luminance value of a first region, which is a region corresponding between the images, and a second luminance profile indicating a change in a luminance value of a second region, which is a region corresponding between the images; and

a detection unit configured to detect a defect in the target object based on the first luminance profile and the second luminance profile.

2. The information processing apparatus according to claim 1, further comprising an illumination control unit configured to switch lighting and extinction of each of the plurality of illumination units in time series,

wherein the images included in the image group are imaged in time series in a state where the lighting and the extinction of each of the plurality of illumination units are switched by the illumination control unit in time series.

3. The information processing apparatus according to claim 1, wherein the images included in the image group are imaged in time series in a state where relative orientations of the target object and the plurality of illumination units change while the target object is being conveyed by a conveyance unit.

4. The information processing apparatus according to claim 1, wherein in a case where the first luminance profile and the second luminance profile are not approximately the same, and profiles obtained by normalizing the first luminance profile and the second luminance profile are approximately the same, the detection unit determines that there is a difference in color between the first region and the second region.

5. The information processing apparatus according to claim 1,

wherein the first luminance profile has the luminance value of the first region of the images as each component,

wherein the second luminance profile has the luminance value of the second region of the images as each component, and

wherein in a case where there is a variation in a ratio between each component of a profile obtained by normalizing the first luminance profile and each component of a profile obtained by normalizing the second luminance profile, the detection unit determines that there is a difference between normal vectors between the first region and the second region.

6. The information processing apparatus according to claim 1,

wherein the first luminance profile has the luminance value of the first region of the images as each component,

wherein the second luminance profile has the luminance value of the second region of the images as each component, and

wherein in a case where a ratio between each component of a profile obtained by normalizing the first luminance profile and each component of a profile obtained by normalizing the second luminance profile is approximately constant, and there are outlier components a ratio between which is significantly different, and the luminance value of either of the outlier components is greater than the luminance values of the other components, the detection unit determines that there is a difference in specularity between the first region and the second region.

7. The information processing apparatus according to claim 1,

wherein the first luminance profile has the luminance value of the first region of the images as each component,

wherein the second luminance profile has the luminance value of the second region of the images as each component, and

wherein in a case where a ratio between each component of a profile obtained by normalizing the first luminance profile and each component of a profile obtained by normalizing the second luminance profile is approximately constant, and there is outlier components a ratio between which is significantly different, and the luminance value of either of the outlier components is smaller than the luminance values of the other components, the detection unit determines that a boundary caused by a shadow occurs between the first region and the second region.

8. The information processing apparatus according to claim 1, wherein the detection unit detects a shape defect, a hue defect, and a gloss defect on a surface of the target object by distinguishing the shape defect, the hue defect, and the gloss defect from each other.

9. The information processing apparatus according to claim 1, wherein the generation unit changes positional relationships between the plurality of illumination units, a conveyance unit, an imaging unit, and the target object based on the first luminance profile and the second luminance profile.

10. The information processing apparatus according to claim 1, further comprising a display unit configured to display an image of a result of distinguishing a type of defect classified by the detection unit.

11. An information processing method for detecting a defect in a target object without using data obtained by prior learning, the information processing method comprising:

acquiring an image group obtained by imaging a target object irradiated with light from a plurality of illumination units placed at a plurality of different positions;

generating a first luminance profile indicating a change in a luminance value of a first region, which is a region corresponding between the images included in the image group, and a second luminance profile indicating a change in a luminance value of a second region, which is a region corresponding between the images; and

detecting a defect in the target object based on the first luminance profile and the second luminance profile.

12. A storage medium having stored thereon a program for causing a computer to function as each unit of an information processing apparatus for detecting a defect in a target object without using data obtained by prior learning, the information processing apparatus comprising:

an acquisition unit configured to acquire an image group obtained by imaging a target object irradiated with light from a plurality of illumination units placed at a plurality of different positions;

a generation unit configured to, based on luminance information of images included in the image group, generate a first luminance profile indicating a change in a luminance value of a first region, which is a region corresponding between the images, and a second luminance profile indicating a change in a luminance value of a second region, which is a region corresponding between the images; and

a detection unit configured to detect a defect in the target object based on the first luminance profile and the second luminance profile.