IP Library Granted Patent US 10,891,725
Granted Patent B2
US 10,891,725 · App. 15/728,905 · Granted Jan 12, 2021

Inspection apparatus and inspection method

Inventor: Yoichi Kigawa (Ibaraki, JP)
Assignee: NITTO DENKO CORPORATION
G06T7/0008G01N21/8851G01N21/95G06T7/001G06T7/0004G01N21/8422G01N2021/8864G06T2207/10024G06T2207/30148
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,891,725
App. No.
15/728,905
Granted
Jan 12, 2021
Kind
B2
Abstract

An inspection apparatus configured to inspect a target for defects, including: an image capturing unit capable of capturing an image of the target as image information having color information including RGB values; and a determination unit configured to determine presence or absence of defects in the target based on the color information of the image information of the image captured by the image capturing unit, wherein the determination unit is configured to define, for each pixel, criteria for determining presence or absence of defects in each pixel of the image information, based on the color information in a defect-free region of the target captured by the image capturing unit, and to filter all pixels in the image information of the image captured by the image capturing unit so as to determine presence or absence of defects in each pixel, based on the defined criteria.

Claims (14)

1. An inspection apparatus configured to inspect a target for defects, comprising:

a camera capturing an image of the target as image information having color information including RGB values; and

a computer configured to determine presence or absence of defects in the target based on the color information of the image information of the image captured by the camera, wherein the computer uses a support vector machine to create defined criteria for each pixel to determine the presence or absence of defects in each pixel of the image information of the target, the support vector machine being trained using each value group of R value, G value, and B value and a corresponding result group for defect determination of R value, G value, and B value of the color information of a training image having a defect-containing region to create boundaries respectively for R value, G value, and B value as the defined criteria, and the defined criteria being a non-linear relationship for each pixel between the color information in a defect-free region of the training image and the defect-containing region of the training image, and

the computer filters all pixels in the image information of the target so as to determine the presence or absence of defects in each pixel, based on the defined criteria.

2. The inspection apparatus according to claim 1 , wherein

the color information further includes HSL values.

3. The inspection apparatus according to claim 1 , wherein

the color information further includes XYZ values.

4. The inspection apparatus according to claim 1 , wherein

the computer is configured to map results of determining the presence or absence of defects in each of all pixels in image information of the image captured by the camera.

5. A method for inspecting a target for defects, comprising:

capturing an image of the target as image information having color information including RGB values;

creating, using a support vector machine, boundaries for R value, G value, and B value as defined criteria for each pixel to determine a presence or absence of defects in each pixel of the image information of the target, by training the support vector machine using each value group of R value, G value, and B value and a corresponding result group for defect determination of R value, G value, and B value of the color information of a training image which includes a defect-containing region, the defined criteria being a non-linear relationship for each pixel between the color information in a defect-free region of the training image and the defect-containing region of the training image; and

determining the presence or absence of defects in each of all pixels in the image information of the target so as to determine presence or absence of defects in the target.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 10, 2017
From: KIGAWA, YOICHI
To: NITTO DENKO CORPORATION
Reel/Frame 043825/0560 →
Priority Claims (1)
JP 2016-226037 · Nov 21, 2016 · national
Continuity (1)
Related Publication 20180144461A1 · May 24, 2018
Cited By (1)
US 12,379,324