公开(公告)号：US20210063376A1

公开(公告)日：2021-03-04

申请号：US17009117

申请日：2020-09-01

Applicant: The NCS Testing Technology Co., Ltd.

Inventor： Dongling LI ,  Weihao WAN ,  Jie LI ,  Haizhou WANG ,  Lei ZHAO ,  Xuejing SHEN ,  Yunhai JIA

IPC: G01N33/204 ,  G01N1/32 ,  G06T7/11 ,  G01N1/40 ,  G06T7/62

Abstract: The invention belongs to the technical field of quantitative statistical distribution analysis for micro-structures of metal materials, and relates to a method for automatic quantitative statistical distribution characterization of dendrite structures in a full view field of metal materials. According to the method based on deep learning in the present invention, dendrite structure feature maps are marked and trained to obtain a corresponding object detection model, so as to carry out automatic identification and marking of dendrite structure centers in a full view field; and in combination with an image processing method, feature parameters in the full view field such as morphology, position, number and spacing of all dendrite structures within a large range are obtained quickly, thereby achieving quantitative statistical distribution characterization of dendrite structures in the metal material. The method is accurate, automatic and efficient, involves a large amount of quantitative statistical distribution information, and is statistically more representative as compared with the traditional measurement of feature sizes of dendrite structures in a single view field.