IP Library Granted Patent US 10,380,457
Granted Patent B2
US 10,380,457 · App. 15/772,825 · Granted Aug 13, 2019

Lead tip position image recognition method and lead tip position image recognition system

Inventors: Masafumi Amano (Okazaki, JP); Shuichiro Kito (Toyota, JP); Taizo Umezaki (Kasugai, JP)
Assignee: FUJI CORPORATION
G06K9/6263G06K9/03G06T1/00H05K13/04
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 10,380,457
App. No.
15/772,825
Granted
Aug 13, 2019
Kind
B2
Abstract

An electronic component picked up and held by a mounting head of a component mounter is moved to an imaging position above a component imaging camera, the tip of the lead of the electronic component is imaged from below by the camera to acquire a lead image, and the lead image is inputted into an image recognition device configured from a neural network or the like and imaged processed so as to output the center position of the tip of the lead. Here, whenever an image processing error occurs, the lead image for which the image processing error occurred is displayed on a display device, and an operator specifies the center position of the tip of the lead in the lead image display on the display device and the specified center position is inputted into the image recognition device.

Claims (31)

1. A lead tip position image recognition method for recognizing a center position of a lead tip of an electronic component to be inserted into a through-hole of a circuit board by processing an image of the lead tip as a lead image captured by a camera using an image recognition device, the lead tip position image recognition method comprising:

a learning process in which an operator specifies the center position of the lead tip in the lead image and learning is performed such that an output when the lead image is inputted into the image recognition device is the center position of the lead tip specified by the operator; and

a recognizing process of inputting the lead image acquired by imaging the lead tip of the electronic component using the camera into the image recognition device and outputting the center position of the lead tip.

2. The lead tip position image recognition method according to claim 1 , wherein

the image recognition device is configured using a neural network.

3. The lead tip position image recognition method according to claim 1 , wherein

in the recognizing process, processing switches to the learning process when an image processing error occurs in which the center position of the lead tip cannot be recognized, and learning is performed such that the output when the lead image for which the image processing error occurred is inputted to the image recognition device is the center position of the lead tip specified by the operator.

4. The lead tip position image recognition method according to claim 1 , wherein

in the learning process, at least one processing is performed on the lead image out of rotation, mapping, brightness alteration, or shape alteration to generate multiple images, and learning is performed such that the output when each of the multiple images are inputted to the image recognition device is the center position of the lead tip specified by the operator.

5. The lead tip position image recognition method according to claim 1 , wherein

the camera is a component imaging camera configured to image from below an electronic component held by a mounting head of a component mounter, and

during an insertion process of inserting the lead of the electronic component by positioning the lead of the electronic component held by the mounting head at the through-hole of the circuit board based on the recognition result of the image recognition device, when a positioning error occurs in which the lead of the electronic component cannot be inserted into the through-hole of the circuit board, processing switches to the learning process, and learning is performed such that the output when the lead image for which the positioning error occurred is inputted to the image recognition device is the center position of the lead tip specified by the operator.

6. A lead tip position image recognition system for recognizing a center position of a lead tip of an electronic component to be inserted into a through-hole of a circuit board by processing an image of the lead tip as a lead image captured by a camera using an image recognition device, the lead tip position image recognition system comprising:

the image recognition device configured to receive a lead image and output the center position of the lead tip;

a learning device configured to learn a relationship between the lead image inputted to the image recognition device and the outputted center position of the lead tip and to send a learning result of the learning to the image recognition device; and

a specifying means configured to be used by an operator to specify the center position of the lead tip,

wherein

the learning device is configured to perform learning such that the center position of the lead tip in the lead image specified by the operator using the specifying means is the output when the lead image is inputted to the image recognition device.

7. A lead tip position image recognition system for recognizing a center position of a lead tip of an electronic component to be inserted into a through-hole of a circuit board by processing an image of the lead tip as a lead image captured by a camera using an image recognition device, the lead tip position image recognition system comprising:

the image recognition device configured to be switchable between a recognition mode in which the image recognition device receives a lead image and outputs the center position of the lead tip, and a learning mode in which learning is performed of a relationship between the inputted lead image and the center position of the lead tip to be output; and a specifying means configured to be used by an operator to specify the center position of the lead tip,

wherein

the image recognition device is configured to, when in the learning mode, perform learning such that the center position of the lead tip in the lead image specified by the operator using the specifying means is the output when the lead image is inputted to the image recognition device.

8. The lead tip position image recognition system according to claim 7 , wherein

the image recognition device is configured using a neural network.

9. The lead tip position image recognition system according to claim 7 , wherein

the image recognition device, when in the recognition mode, switches to the learning mode when an image processing error occurs in which the center position of the lead tip in the image cannot be recognized, and learning is performed such that the output when the lead image for which the image processing error occurred is inputted to the image recognition device is the center position of the lead tip specified by the operator.

10. The lead tip position image recognition system according to claim 7 , wherein

the image recognition device, when in the learning mode, performs processing such that at least one out of rotation, mapping, brightness alteration, or shape alteration is performed on the lead image to generate multiple images, and performs learning such that the output when each of the multiple images are inputted to the image recognition device is the center position of the lead tip specified by the operator.

11. The lead tip position image recognition system according to claim 7 , wherein

the camera is a component imaging camera configured to image from below an electronic component held by a mounting head of a component mounter, and

during an insertion process of inserting the lead of the electronic component by positioning the lead of the electronic component held by the mounting head at the through-hole of the circuit board based on the recognition result of the image recognition device, when a positioning error occurs in which the lead of the electronic component cannot be inserted into the through-hole of the circuit board, processing switches to the learning mode, and learning is performed such that the output when the lead image for which the positioning error occurred is inputted to the image recognition device is the center position of the lead tip specified by the operator.

Assignments (2)
CHANGE OF NAME Recorded May 15, 2018
From: FUJI MACHINE MFG. CO., LTD.
To: FUJI CORPORATION
Reel/Frame 046153/0748 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 2, 2018
From: AMANO, MASAFUMI; KITO, SHUICHIRO; UMEZAKI, TAIZO
To: FUJI MACHINE MFG. CO., LTD.
Reel/Frame 045689/0365 →
Continuity (1)
Related Publication 20180314918A1 · Nov 1, 2018