The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 17, 2025

Filed:

May. 12, 2021
Applicants:

Te Connectivity Services Gmbh, Schaffhausen, CH;

Tyco Electronics (Shanghai) Co., Ltd., Shanghai, CN;

Tyco Electronics Mexico, S. DE R.l. DE C.v., Tlalnepantla, MX;

Inventors:

Sonny O. Osunkwo, Harrisburg, PA (US);

Roberto Francisco-Yi Lu, Bellevue, WA (US);

Jiankun Zhou, Middletown, PA (US);

Lei Zhou, Shanghai, CN;

Angel Alberto Slistan, Hermosillo Sonora, MX;

Dandan Zhang, Shanghai, CN;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06T 7/00 (2017.01); G06N 3/04 (2023.01);
U.S. Cl.
CPC ...
G06T 7/0004 (2013.01); G06N 3/04 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30164 (2013.01);
Abstract

A part inspection system is provided and includes a vision device configured to image a part is inspected and generate a digital image of the part. The part inspection system includes a part inspection module coupled to the vision device and receiving the digital image of the part. The part inspection module includes a memory for storing a neural network architecture having a plurality of convolutional layers, a plurality of pooling layers disposed after different convolutional layers and spaced apart from each other, at least one random noise generation layer downstream of the convolutional layers and the pooling layers, and an output layer. The part inspection module includes a processor configured to analyze the digital image through the layers of the neural network architecture to output one of a defective output or a non-defective output based on the image analysis of the digital image through the neural network architecture.


Find Patent Forward Citations

Loading…