A corner-clustering method for detection of slab management numbers sprayed on steel slabs
- PDF / 2,545,623 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 41 Downloads / 145 Views
ORIGINAL ARTICLE
A corner-clustering method for detection of slab management numbers sprayed on steel slabs Yiping Peng1 · Junhui Ge1 · Hui Qin1 · Xiaojun Ge1 · Changyan Xiao1 Accepted: 4 November 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract To achieve manufacturing and logistics informatization management for steelworks, it is of crucial importance to automatically recognize the slab management numbers (SMNs) sprayed on the steel slabs. However, due to the poor quality of spraying and various interferences, SMN detection is a major challenge for subsequent recognition in the steel-slab product line. This paper proposes a corner-clustering method, which can extract the SMN from a changeable background precisely and promptly. In our method, the FAST algorithm is modified to extract the image corners by adaptively adjusting the local threshold of corner detecting with the change of image contrast. Then, the DBSCAN algorithm is implemented to group the corners into several clusters, which includes the SMN regions and interference regions. Finally, a classifier based on HOG features and SVM is applied to discriminate SMN and non-SMN regions. For experimental validation, the proposed method was implemented to a substantial amount of acquired images. A good performance has been achieved as the detection accuracy can reach as high as 98.96% for SMN on the steel slabs. Keywords SMN detection · Computer vision · Steel slabs · DBSCAN cluster · Corner detection
1 Introduction In steel mills, each product, slab, is marked with a unique identification number, named SMN (slab management number: a label consisting of a sequence of alphabets, digits, and special symbols), which provides important information, such as manufacturer, material, specification, production time, and serial number of steel products. Presently, to manage and track the steel products in real time, manual operation still takes a large proportion in identifying the SMN labels in the complex production line. However, manual operation for the tedious and repetitive work is highly labor intensive and low effective. Besides, reliability and effectiveness can be enhanced to a large extent by an autonomous system. Therefore, it is essential and urgent to recognize the SMN label automatically. Due to the ever-increasing development and pervasive application of computer vision in industry [1,2], steel mills realize capturing images with a camera and extracting infor-
B 1
Changyan Xiao [email protected] National Engineering Laboratory for Robot Visual Perception and Control Technology, Hunan University, Changsha, China
mation on the steel slabs is of great value to achieve manufacturing and logistics informatization management. Thus, many of them attempt to automatically recognize SMN labels to replace manual operation. In our industrial setting, the image acquisition system set for a production line is presented in Fig. 1, which consists of a line scanning camera and light sources. The line scanning camera is mounted on the top to
Data Loading...
