Title :
Fast and high accuracy pattern matching using multi-stage refining eigen template
Author :
Koutaki, Gou ; Yata, K. ; Uchimura, Keiichi ; Kan, Masaki ; Asai, D. ; Takeba, M.
Author_Institution :
Kumamoto Univ., Kumamoto, Japan
Abstract :
Template matching is the basic technique of the image processing for the object detection such as OCR(Optical Character Recognition), Face detection, and the defect inspection. The template matching can detect the XY displacement and the rotational angle of the target object from the input image captured by the camera. We have proposed the eigen template method for the template matching problem. Eigen template method can reduce the times of convolution than previous rotational template matching. However, the computation time remains large still. In this paper, we propose an efficient search algorithm using multi-stage refining process for the eigen template matching. In the experiments, we show that the proposed method can detect the target object fast with high accuracy compared with the previous methods.
Keywords :
cameras; convolution; eigenvalues and eigenfunctions; image matching; object detection; search problems; camera; convolution time reduction; displacement detection; eigen template matching; image processing; multistage refining process; object detection; pattern matching; rotational angle detection; rotational template matching; search algorithm; Accuracy; Correlation; Equations; Estimation; Mathematical model; Refining; Shape;
Conference_Titel :
Frontiers of Computer Vision, (FCV), 2013 19th Korea-Japan Joint Workshop on
Conference_Location :
Incheon
Print_ISBN :
978-1-4673-5620-6
DOI :
10.1109/FCV.2013.6485460