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. 30, 2020

Filed:

Nov. 20, 2019
Applicant:

Republic of Korea (National Forensic Service Director Ministry of Public Administration and Security), Wonju-si, Gangwon-do, KR;

Inventors:

Nam Kyu Park, Bucheon-si, KR;

Jae Mo Goh, Wonju-si, KR;

Jin Pyo Kim, Daejeon, KR;

Young Il Seo, Wonju-si, KR;

Eun Ah Joo, Yongin-si, KR;

Je Hyun Lee, Wonju-si, KR;

Sang Yoon Lee, Wonju-si, KR;

Dong A Lim, Daejeon, KR;

Kyung Mi Kim, Namyangju-si, KR;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 20/00 (2019.01); G01N 21/88 (2006.01); G06K 9/62 (2006.01);
U.S. Cl.
CPC ...
G01N 21/8851 (2013.01); G06K 9/6202 (2013.01); G06K 9/6256 (2013.01); G06N 20/00 (2019.01); G01N 2021/8887 (2013.01);
Abstract

According to an embodiment, a method of determining tool mark identity using machine learning may include: obtaining surface height data of at least two tool strip marks by photographing tool strip marks generated using at least two tools with a three-dimensional (3D) microscope; generating a data set by calculating a cross-correlation coefficient for the surface height data of the tool strip marks; separating the data set into a training set for machine learning training and a test set for verifying a machine learning result; performing the machine learning training to determine whether the tool strip marks are identical using the training set; and verifying a result of the machine learning training using the test set.


Find Patent Forward Citations

Loading…