• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.729-732
• /
• 2002

본 논문에서는 대부분의 지문 인식 알고리즘에서 전처리에 해당하는 부분인 이미지 세선화에 관한 연구이다. 기존의 알고리즘을 보면 지운 매칭을 하기 전에 이미지 이진화와 세선화, 방향성 추출, 특징점 추물을 거친 후에 지문의 매칭이 이루어지는 단계이다. 이런 단계를 줄이기 위해 본 논문에서는 세선화 과정에서 기존의 알고리즘을 쓰지않고 융선을 추적해 나가는 방법으로 세선화를 함과 동시에 방향성 추출과 특징점 추출을 함께 해 나갈 수 있는 방향을 제시하고 있다. 이렇게 됨으로써 인식 시간을 단축할 수 있다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.2
• /
• pp.90-94
• /
• 2013

Research for Manchu character digitalization is at an early stage. This paper proposes a preprocessing algorithm for Manchu character recognition. This algorithm improves the existing Hilditch thinning algorithm so that it corrects thinning error for Manchu characters. The existing algorithm separates the characters into the left-hand side and right-hand side, while our alogorithm uses the central point between the points that strokes exist when it classifies each of characters. The experimentation results show that this method is valid for thinning and classification of Manchu characters.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.2
• /
• pp.21-29
• /
• 2003

The thinning algorithms using 8-neighbors connection value can extract the skeleton of a character almost similar to the original pattern by using the connection value representing connectivity of each pixel. This paper considers the erosion phenomenon which appears in the thinning algorithm using 8-neighbors connection value without skeleton disappearance phenomenon. The experimental results show that the proposed thinning algorithm can be applied to the application of both a straight line segment and a curved line segment.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.1
• /
• pp.1-6
• /
• 2009

A Thinning algorithm is a very Important factor in order to recognize the character, figure, and drawing. Until comparatively lately, the thinning algorithm was proposed by various methods. In this paper, we ascertain the point at issue of ZS(Zhang and Suen), LW(Lu and Wang) and WHF(Wang, Hui and Fleming) algorithms that are the parallel thinning algorithms. The parallel thinning algorithm means the first processing doesn't have to influence to the second processing. ZS algorithm has a problem which loses pixels in slanting lines and LW algorithm doesn't have one pixel width in slanting lines. So I propose an advanced parallel thinning algorithm that connects the pixels each other and preserve the end point.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.719-721
• /
• 2013

A thinning stage of fingerprint algorithm occupies 39% cycle of microprocessor system for identification processing of image from fingerprint sensor. Hardware block processing is more effective than software one in speed and power consumption, because a thinning algorithm is iteration of simple instructions without a transcendental function. This paper describes an effective hardware scheme for thinning stage processing using Verilog-HDL in $64{\times}64$ Pixel Array. The hardware scheme is designed and simulated in RTL. The logic is also synthesized by XST in FPGA environment and tested. Experimental results show the performance of the proposed scheme and possibility of application for a soft microprocessor and thinning processor embedded fingerprint SoC.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.5
• /
• pp.883-891
• /
• 1994

In this paper, we introduce new thinning algorithm which is useful for handwritten Korean character by using pixel directivity. At first, the directivity detection is performed before thinning. Each pixel is classified into the straight line of the oblique line based on its directivity. The algorithm using Rutovitz corossing number is applied to the straight line. And the algorithm using Hilditch crossing number is applied to the oblique line. The proposed algorithm is compared with six convention algorithms. Comparison criteria are similarity, noisy branch, and phoneme segmentation rate. Experiments with 570 characters have been conducted. Experimental result shows that the proposed algorithm is superior to six conventional algorithm with respect to similarity and phoneme segmentation rate.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.1
• /
• pp.54-62
• /
• 1999

Vectorizing for input processing of map is the most time and cost consuming task, and the quality of vector data depends on that processing result. Therefore, it is an important task to develop a good vectorizing system in the GIS. Thinning algorithm is the most important technology for deciding the quality of vector data in the vectorizing system. In this paper, as a suitable algorithm for map vectorizing we considered several algorithms that preserve topological and geometric characteristics, and have no distortion of the contour line. As a results, we implemented WPTA4 and well known thinning algorithm, and compared WPTA4 execution results with the others.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.277-281
• /
• 2002

본 논문에서는 '지문 인식의 전처리 과정 단축에 관한 연구'의 알고리즘의 구현에 대한 내용을 언급했으며, 향우 보완에 대한 내용을 다루고 있다[6]. 기존의 알고리즘을 보면 지문 매칭을 하기 전에 이미지 이진화와 세선화, 방향성 추출, 특징점 추출을 거친 후에 지문의 매칭이 이루어지는 단계이다. 이런 단계를 줄이기 위해 논문에서는 세선화 과정에서 기존의 알고리즘을 쓰지 않고 융선을 추적해 나가는 방법으로 세선화를 함과 동시에 방향성 추출과 특징점 추출을 함께 해 나갈 수 있는 방향을 제시하고 있다. 이렇게 됨으로써 인식 시간을 단축 할 수 있다.

• Korean Journal of Cognitive Science
• /
• v.2 no.2
• /
• pp.341-358
• /
• 1990

In this paper, A thinning algorithm which can solve a noise problem os proposed. The proposed method is based on the pavlidis thinning algorithm. During a contour tracing period of the given image, the masks of $3{\times}3$ pixels are proposed. They check all possible caseds of the noise conditions. As soon as the contour tracing is finished, the candidates of the noise are automatically deleted. As a result of the implementation of the proposed algorithm, the similar results which is obtained by noise-free image are obtained and they show the simplified structures comparing with the thinning results of the noisy images. Thus, They illustrate that a simple recognition part is needed to identify the objects.

• Korean Journal of Cognitive Science
• /
• v.7 no.1
• /
• pp.5-35
• /
• 1996

This paper addresses an one-pass parallel thinning algorithm which shows effectiveness in both accuracy and speed. The proposed method is based on parallel iterative boundary removal.Image connectivity are preseved and the algorithms performance is compared to other algorithms especially to parallel thinning algorithm which is the best parallel algorithm have been proposed.Evaluation result shows that the proposed algorithm compare favorably to others.The result shows exact thinning free from one pixel boundary noise and free from distortion of shape.