• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1598-1601
• /
• 1987

This paper proposes a new set of topological features (primitives) for use with a syntactic recognizer for high-accuracy recognition of printed alphanumeric characters. The recognition is accomplished on nine character groups, where each group has different combinations of four feature points. A skeleton enhancement eliminating isolated points and smoothing irregular points is developed. The tree automata processed in parallel enables the realization of high-recognition speeds and font-type independent recognition. The proposed character recognition system is tested for alphanumeric character fonts of dot matrix printer and plotter using IBM-PC/XT.

• 한국게임학회 논문지
• /
• 제3권2호
• /
• pp.24-29
• /
• 2003

The market of digital avatar with internet and digital technology is increasing rapidly. The users want to express any free-formed motion of their avatars in the cyber space. The user s motion capturing method as the avatar's motion can express any free-formed motion of the avatar in real-time but the methods are expensive and inconvenient. In this paper, we proposed a new method of expressing any free-formed motion of the avatar in real-time. The proposed method is an algorithm for real-time control of a 3D avatar in symmetry-formed free motion. Specially, the algorithm aims at the motion control of a 3D avatar for online dancing games. The proposed algorithm uses the skeleton character model and controls any one of two hands of the character model by a joystick with two sticks. In the symmetry-formed motion, the position and orientation of one hand can determine the position and orientation of the other hand. And the position and orientation of a hand as an end-effector can determine the pose of the arm by Inverse Kinematics. So the algorithm can control the symmetry-formed free motions of two arms by one joystick with two sticks. In the dance game, the algorithm controls the arm motion by the joystick and the other motion by the motion captured DB.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.819-822
• /
• 2000

The merit of the stroke extraction algorithm is the ease of the feature abstraction from the skeleton of a character, But, extracting strokes from Korean characters has two major problems that must be dealt with. One is extracting primitive strokes and the other is merging or splitting the strokes using dynamic information of the strokes. In this paper, a method is proposed to extract strokes from an off-line handwritten Korean character. We have developed some stroke segmentation rules based on splitting, merging and directional analysis. Using these techniques, we can extract and trace the strokes in an off-line handwritten Korean character accurately and efficiently.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.1-13
• /
• 2021

In this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.

• 정보처리학회논문지B
• /
• 제9B권4호
• /
• pp.481-490
• /
• 2002

오프라인 필기체 문자 인식은 동적인 정보를 가지고 있지 않고, 다양한 필기와 자음과 모음의 겹침이 심하며, 획 사이의 잡영을 많이 가지고 있어 불완전한 전처리를 수행하여야 하는 어려움이 있다. 따라서 오프라인 필기체 문자 인식은 다양한 방법의 전처리 즉 이진화 및 세선화에 대한 연구가 필요하다. 본 논문에서는 오프라인 필기체 한글 문자 인식의 전처리로서 워터쉐드 알고리즘의 수행 시간과 결과 영상의 품질을 고려해 그레이 레벨 문자 영상에서의 문자 영역과 배경 영역의 분할을 위한 효과적인 워터쉐드 알고리즘의 적용 방법과 추출된 워터쉐드 영상을 이진화하는 분할 함수를 제안한다. 또한 수행 시간과 골격선의 품질을 고려한 조건 검사 마스크를 통해서 효과적으로 골격선을 추출하는 세선화 방법을 제안하고 기존의 방법과 본 논문 방법을 수행 시간과 품질로써 성능을 평가한다. 실험 결과 기존의 방법은 평균 2.16초, 본 논문 방법은 평균 1.72초의 수행 시간이 걸렸다. 또한 결과 영상의 품질은 본 논문 방법이 문자 획 사이의 잡영을 효과적으로 처리함을 알 수 있었다.

• 복식
• /
• 제57권3호
• /
• pp.1-13
• /
• 2007

The Purpose of this study is to analyze the kinds and positions of tattoo patterns on the body in tattoo-related internet communities and professional web sites. for this purpose, 1,892 tattoo patterns were analyzed by sex(man and woman). The results were as fellows; First, animal patterns(30.2%) occupied most, followed by character patterns(24.1%), geometric patterns(13.0%), natural patterns(10.3%), plant patterns(4.7%), mixed patterns(2.5%), and artificial patterns(2.2%). In patterns, dragon(10.3%) occupied most, followed by star(8.7%), trival(8.6%), woman(7.6%), skeleton(4.9%), and letter(4.8%). Second, men's preference to pattern groups included animal patterns(30.8%), character patterns (28.3%), geometric patterns (14.6%), and natural patterns(6.0%). Among patterns, dragon(13.4%) was the most frequent, followed by trival(10.9%), woman(10.7%), and skeleton(7.1%). Women's preference to patterns groups included animal patterns(31.4%), natural patterns(17.3%), character patterns(17.2%), geometric patterns(10.5%), and plant patterns(10.0%). Among patterns, star(15.3%) was the most frequent, followed by butter- fly(10.5%), elf(9.2%), and dragon(9.2%). Third, the positions of tattoos on the body included upper arm(26.6%), shoulder(10.8%), back(10.5%), the wrist(10.0%), the calf(7.5%), back bottom(7.0%) and the breast(6.3%). While men's preference to pattern positions included upper arm(38.2%), the wrist(13.7%), back(10.5%), the calf(9.4%), and shoulder(8.0%), women's preference to positions included back bottom(17.7%), shoulder(15.5%), back(10.5%), front bottom(8.2%), and the breast(7.8%).

• International Journal of Contents
• /
• 제11권3호
• /
• pp.7-13
• /
• 2015

One of the biggest problems of skeletonization is the occurrence of distortions at the junction point of the final binary image. At the junction area, a single point usually becomes a small stroke, and the corresponding trajectory task, as well as the OCR, consequently becomes more complicated. We therefore propose an adaptive post-processing method that uses an adaptive threshold technique to correct the distortions. Our proposed method transforms the distorted segments into a single point so that they are as similar to the original image as possible, and this improves the static handwriting images after the skeletonization process. Further, we attained promising results regarding the usage of the enhanced skeletonized images in other applications, thereby proving the expediency and efficiency of the proposed method.

• International Journal of Contents
• /
• 제14권2호
• /
• pp.41-44
• /
• 2018

In this paper, we propose a novel method for developing expressive typography authoring tools with personal emotions. Our goal is to implement an interactive typography system that does not rely on any particular language and provides an easy, natural user interface and allows for immediate interaction. For this purpose, we converted the text data entered by a user to image data. The image data was then used for interaction with the user. The data was synchronized with the user's skeleton information obtained from the depth camera. We decomposed the characters using the formality of language to provide a typographical movement that responds more dynamically to the user's motion. Thus, this system provides interaction as a unit of characters rather than as a whole character, allowing the user to have emotional and aesthetic emotional immersion into his or her creation.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 춘계학술대회
• /
• pp.521-523
• /
• 2012

가상현실이나 게임 제작 분야에서는 사실적이고 실시간으로 캐릭터의 동작을 생성해야 하는 경우가 빈번하다. 특히, 인체를 비롯한 다관절체의 동작 생성에 있어서는 지형이나 다른 주변 환경에 의한 적응적인 동작의 필요성이 증가하고 있다. 본 논문은 지형의 변화나 다른 주변 환경에 의한 적응적인 동작을 구현해 어떠한 동작이 가장 자연스럽고 실시간으로 적응될 수 있는지 분석하고 캐릭터 애니메이션을 구현한다. 이를 위해 캐릭터의 다양한 움직임을 제어하기 위해 인체의 주요 관절들을 부각시켜 인체 모형 캐릭터를 키네마틱 애니메이션 방식으로 생성하기로 한다. 지형의 변화는 고저차이가 발생할 수 있는 계단 환경에서의 동작을 분석하고 다른 주변 환경에 의한 적응적인 동작은 경사면을 올라가는 동작을 분석하여 이를 토대로 캐릭터 애니메이션을 구현한다.

• 전자공학회논문지B
• /
• 제30B권6호
• /
• pp.76-85
• /
• 1993

In this paper, we propose a stroke matching method for the off-line recognition of handprinted Hangul. In this method, the preprocessing steps such as position normalization, contour tracing and thinning are carried out first. Then, after extracting features such as the firection component distribution of contour, the direction component distribution of skeleton, and the distribution of structural feature points, strokes are extracted and matched based on the midpont distribution of the direction and the length of each stroke. In order to reduce the recognition time, a preliminary classification based on the direction component distribution features of the contour is performed. In order to domonstrate the performance of the proposed method, experiments with 520 most frequently used Hangul were performed, and 90.7% of correct recognition rate and 0.46second of recognition time per one character has been obtained. This results reveal that the proposed method can absorb effectively the noise in input character and the variations of stroke slant.