%0 Journal Article
	%A Jaedo Kim and  Youngjoon Han and  Hernsoo Hahn
	%D 2009
	%J International Journal of Computer and Information Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 32, 2009
	%T Character Segmentation Method for a License Plate with Topological Transform
	%U https://publications.waset.org/pdf/1727
	%V 32
	%X This paper propose the robust character segmentation method for license plate with topological transform such as twist,rotation. The first step of the proposed method is to find a candidate region for character and license plate. The character or license plate
must be appeared as closed loop in the edge image. In the case of
detecting candidate for character region, the evaluation of detected
region is using topological relationship between each character. When
this method decides license plate candidate region, character features
in the region with binarization are used. After binarization for the detected candidate region, each character region is decided again. In
this step, each character region is fitted more than previous step. In the
next step, the method checks other character regions with different
scale near the detected character regions, because most license plates
have license numbers with some meaningful characters around them.
The method uses perspective projection for geometrical normalization.
If there is topological distortion in the character region, the method
projects the region on a template which is defined as standard license
plate using perspective projection. In this step, the method is able to
separate each number region and small meaningful characters. The
evaluation results are tested with a number of test images.
	%P 2147 - 2150