제어로봇시스템학회:학술대회논문집

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

Recognition of Object ID marks in FA process from Active Template Model

  • Kang, Dong-Joong (College of Information Engineering, Tongmyong University of IT) ;
  • Ahn, In-Mo (Division of Computer and Electrical Engineering, Masan College) ;
  • Lho, Tae-Jung (College of Information Engineering, Tongmyong University of IT) ;
  • An, Hyung-Keun (College of Information Engineering, Tongmyong University of IT) ;
  • Yoo, Dong-Hun (College of Information Engineering, Tongmyong University of IT) ;
  • Kim, Mun-Jo (College of Information Engineering, Tongmyong University of IT)
  • Published : 2003.10.22
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a method to segment object ID marks on poor quality images under uncontrolled lighting conditions of FA inspection process. The method is based on multiple templates and normalized gray-level correlation (NGC) method. We propose a multiple template method, called as ATM (Active Template Model) which uses combinational relation of multiple templates from model templates to match and segment several characters of the inspection images. Conventional Snakes algorithm provides a good methodology to model the functional of ATM. To increase the computation speed to segment the ID mark regions, we introduce the Dynamic Programming based algorithm. Experimental results using images from real FA environment are presented.

Keywords