Analysis device and analysis method

Patent metadata

Field	Value
Publication number	US-12462539-B2
Application number	US-202117792435-A
Country	US
Kind code	B2
Filing date	Feb 2, 2021
Priority date	Feb 12, 2020
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

An analysis device for visualizing an accuracy of a trained determination device includes an acquisition unit acquiring an image pair of a non-defective product image and a defective product image, an extraction unit extracting an image region of a defective part of the defective product, a generation unit generating a plurality of image regions of pseudo-defective parts, a compositing unit synthesizing each of the image regions of the plurality of pseudo-defective parts with the non-defective product image to generate a plurality of composite images having different feature quantities, an unit outputting the plurality of composite images to the determination device and acquiring a label corresponding to each of the plurality of composite images from the determination device, and a display control unit displaying an object indicating the label corresponding to each of the plurality of composite images in an array based on the feature quantities.

First claim

The invention claimed is:

1 . An analysis device comprising:
a memory storing a plurality of instructions; and a processor, wherein the plurality of instructions are configured to cause the processor to:
acquire an image pair of a non-defective product image with a non-defective product as a first subject and a defective product image with a defective product as a second subject;
extract an image region of a defective part of the defective product on a basis of the image pair;
change a feature quantity of the image region of the defective part to generate a plurality of image regions of pseudo-defective parts;
synthesize image regions of a plurality of pseudo-defective parts with the non-defective product image to generate a plurality of composite images having different feature quantities of the plurality of pseudo-defective parts;
determine a label corresponding to each of the plurality of composite images, wherein: i) a non-defective product label indicates that a product in an image is the non-defective product and ii) a defective product label indicates that the product in the image is the defective product; and
display an object indicating the label corresponding to each of the plurality of composite images in an array based on feature quantities, wherein the array is a graph displayed on an output device for viewing by an operator.

2 . The analysis device according to claim 1 , wherein the plurality of instructions are further configured to cause the processor to display the plurality of composite images and the object.

3 . The analysis device according to claim 1 , wherein the plurality of instructions are further configured to cause the processor to assign a tag corresponding to a composite image on a basis of a user operation.

4 . The analysis device according to claim 3 , wherein the plurality of instructions are further configured to cause the processor to perform training on a basis of the composite image and the tag corresponding to the composite image.

5 . An analysis method comprising:
acquiring an image pair of a non-defective product image with a non-defective product as a first subject and a defective product image with a defective product as a second subject; extracting an image region of a defective part of the defective product on a basis of the image pair; changing a feature quantity of the image region of the defective part to generate a plurality of image regions of pseudo-defective parts; synthesizing image regions of a plurality of pseudo-defective parts with the non-defective product image to generate a plurality of composite images having different feature quantities of the plurality of pseudo-defective parts; determining a label corresponding to each of the plurality of composite images, wherein: i) a non-defective product label indicates that a product in an image is the non-defective product and ii) a defective product label indicates that the product in the image is the defective product; and displaying an object indicating the label corresponding to each of the plurality of composite images in an array based on feature quantities, wherein the array is a graph displayed on an output device for viewing by an operator.

Assignees

• Morpho Inc
• Tokyo Weld Co Ltd

Inventors

• Yokoyama Yoshihiko
• Kato Tsukasa
• Kikuchi Daiju
• Hirota Satoshi
• Umeno Takuma

Classifications

• G06T2207/30108

  Industrial image inspection · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T7/0004 Primary

  Industrial image inspection · CPC title

• G06V10/945

  User interactive design; Environments; Toolboxes · CPC title