• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.37-44
• /
• 2006

In this paper, a new version of the ICM method(MICM, modified ICM) in which the contextual information is modelled by Markov random fields (MRF) is introduced. To extract the feature, a new local MRF model with a fitting block neighbourhood is proposed. This model selects contextual information not only from the relative intensity levels but also from the geometrically directional position of neighbouring cliques. Feature extraction depends on each block's contribution to the local variance. They discriminates it into several regions, for example context and background. Boundaries between these regions are also distinctive. The proposed algerian performs segmentation using directional block fitting procedure which confines merging to spatially adjacent elements and generates a partition such that pixels in unified cluster have a homogeneous intensity level. From experiment with ink rubbed copy images(Takbon, 拓本), this method is determined to be quite effective for feature identification. In particular, the new algorithm preserves the details of the images well without over- and under-smoothing problem occurring in general iterated conditional modes (ICM). And also, it may be noted that this method is applicable to the handwriting recognition.

• Journal of Korea Multimedia Society
• /
• v.3 no.5
• /
• pp.433-444
• /
• 2000

The recognition of car plate was investigated by means of the enhanced fuzzy ART algorithm. The morphological information of horizontal and vertical edges was used to extract a plate area from a car image. In addition, the contour tracking algorithm by utilizing the SOFM was applied to extract the specific area which includes characters from an extracted plate area. The extracted characteristic area was recognized by using the enhanced fuzzy ART algorithm. In this study we propose the novel fuzzy ART algorithm different from the conventional fuzzy ART algorithm by the dynamical establishment of the vigilance threshold which shows a tolerance limit of unbalance between voluntary and saved patterns for clustering. The extraction rate obtained by using the morphological information of horizontal and vertical edges showed better results than that from the color information of RGB and HSI. Furthermore, the recognition rate of the enhanced fuzzy ART algorithm was improved much more than that of the conventional fuzzy ART and SOFM algorithms.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.528-538
• /
• 2003

A SCCRS (Speech and Character Combined Recognition System) is developed for working on mobile devices such as PDA (Personal Digital Assistants). In SCCRS, the feature extraction is separately carried out for speech and for hand-written character, but the recognition is performed in a common engine. The recognition engine employs essentially CHMM (Continuous Hidden Markov Model), which consists of variable parameter topology in order to minimize the number of model parameters and to reduce recognition time. For generating contort independent variable parameter model, we propose the SSMS(Successive State and Mixture Splitting), which gives appropriate numbers of mixture and of states through splitting in mixture domain and in time domain. The recognition results show that the proposed SSMS method can reduce the total number of GOPDD (Gaussian Output Probability Density Distribution) up to 40.0% compared to the conventional method with fixed parameter model, at the same recognition performance in speech recognition system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.5
• /
• pp.1052-1061
• /
• 2003

In this paper, we propose the car plate recognition using SOM algorithm and describe the parking control system using the proposed car plate recognition. The recognition of car plate was investigated by means of the SOM algorithm. The morphological information of horizontal and vertical edges was used to extract a plate area from a car image. In addition, the 4-direction contour tracking algorithm was applied to extract the specific area, which includes characters from an extracted plate area. The extracted characteristic area was recognized by using the SOM algorithm. In this paper, 50 car images were tested. The extraction rate obtained by the proposed extraction method showed better results than that from the color information of RGB and HSI, respectively. And the car plate recognition using SOM algorithm was very efficient. We develop the parking control system using the proposed car plate recognition that shows performance improvement by the experimental results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.1
• /
• pp.185-196
• /
• 1999

In this dissertation, a new off-line recognition system is proposed using a subgraph pattern, neural network. After thinning is applied to input characters, balance having a noise elimination function on location is performed. Then as the first step for recognition procedure, circular elements are extracted and recognized. From the subblock HT, space feature points such as endpoint, flex point, bridge point are extracted and a subgraph pattern is formed observing the relations among them. A region where vowel can exist is allocated and a candidate point of the vowel is extracted. Then, using the subgraph pattern dictionary, a vowel is recognized. A same method is applied to extract horizontal vowels and the vowel is recognized through a simple structural analysis. For verification of recognition subgraph in this paper, experiments are done with the most frequently used Myngjo font, Gothic font for printed characters and handwritten characters. In case of Gothic font, character recognition rate was 98.9%. For Myngjo font characters, the recognition rate was 98.2%. For handwritten characters, the recognition rate was 92.5%. The total recognition rate was 94.8% with mixed handwriting and printing characters for multi-font recognition.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.126-131
• /
• 1989

본 논문에서는 Error Back Propagation 학습을 이용해 한글 문자를 On-Line 인식하는 시스템을 제안한다. Pointing device의 궤적을 추적해 입력 패턴의 특징(feature)을 추출해 신경 회로망 입력으로 준다. 이때 사용하는 특징은 기본 획 (stroke)의 종류 및 획간의 상대적 위치 관계이다. 학습과정에서는 자소의 정의를 읽어 초성, 중성, 종성에 대해 각 획수마다 정의된 신경회로망의 weight를 조정한다. 인식 과정에서는 초성, 중성, 종성의 순으로 에러가 최소인 획수의 신경회로망 출력을 택하여 2 바이트 조합형 코드로 완성한다. 이로써 Intelligent Man-Machine Interface 시스템중 위치 및 크기에 무관한 전필 입력 시스템을 구현한다.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.57-61
• /
• 2002

대부분의 공문서들이 주민등록증에 기입된 정보들을 반복적으로 기입하도록 요구하는 경우가 많다. 자동으로 주민 정보들을 기입하기 위해서 기계적으로 해독 가능한 정보로는 현재 주민등록증의 이미지만이 가능하다. 본 연구에서는 주민등록증을 스캐닝해서 얻은 이미지에서 주민번호를 추출하여, 개인신용정보의 조회나 반복적인 서류 작성에 개인정보들이 자동으로 기입되는 시스템을 개발하였다. 주민증의 이미지에는 사진과 위조 방지 문양, 그리고 성명, 주소, 주민번호 등의 문자 정보들이 들어있는데, 이 중에서 주민번호 숫자만 추출하였다. 이렇게 인식된 주민번호를 이용해서, 전산화가 되어 있는 주민 정보와의 대조를 할 수 있게 하였고, 개인 정보들을 XML로 정리하여 각종 문서 양식에 자동으로 기입될 수 있도록 하였다. 위조방지문양과 스캐너의 잡음 등에 기인한 왜곡을 해소하기 위해, 히스토그램 기법을 이용하여 숫자영역을 분리하고, 이진화한 다음, 특징점(끝점, 교차점, 분기점)의 정보와 ART1를 사용하여 숫자들을 분류하였다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.11
• /
• pp.102-110
• /
• 1992

In this paper, a new method of character recognition is proposed. It uses density information, in addition to positional and directional information generally used, to recognize a character. Four directional feature primitives are extracted from the thinning templates on the observation that the output of the templates have directional property in general. A simple and fast feature extraction scheme is possible. Features are organized from recursive nonary tree(N-tree) that corresponds to normalized character area. Each node of the N-tree has four directional features that are sum of the features of it's nine sub-nodes. Every feature primitive from the templates are added to the corresponding leaf and then summed to the upper nodes successively. Recognition can be accomplished by using appropriate feature level of N-tree. Also, effectiveness of each node's feature vector was tested by experiment. A method to implement the proposed feature vector organization algorithm into hardware is proposed as well. The third generation node, which is 4$\times$4, is used as a unit processing element to extract features, and it was implemented in hardware. As a result, we could observe that it is possible to extract feature vector for real-time processing.

• Journal of KIISE:Software and Applications
• /
• v.28 no.8
• /
• pp.570-581
• /
• 2001

본 논문에서는 윤곽선(edge) 기반의 형태 정보와 웨이브렛 변환(wavelet transform)에 의한 방향(direction) 정보를 사요하는데 2단계 상표 영상 검색 시스템을 제안한다. 1 단계에서는 후보 상표 영상을 추출하기 위해 영상의 전반적인 정보로 원 상표 영상(original trademark image)을 웨이브렛 변환하여 얻은 X, Y 방향 고주파(high frequency) 성분으로부터 구한 방향 정보와 영상의 윤곽선에 대해 모멘트를 구하는 향상된 불변 모멘트(improved invariant moment)를 이용한다. 2단계에서는 후부 영상들에 대해 영상의 세부 정보인 윤곽선 각도(edge angle)와 윤곽선 반지름(edge radius) 정보를 추출하여 유사도 측정 알고리즘을 통해 결과 영상을 산출하게 된다. 본 상표 영상 검색 시스템은 문자 색인으로는 색인이 용이 하지 않은 기하학적도형 상표 영상만을 사용하였다. 본 시스템에서는 색상과는 상관없는 특징인 형태 정보와 방향 정보만을 이용하므로 같은 색상 구성을 가진 유사 영상뿐만 아니라, 유사하지만 바탕이 반전된 영상이나 색상이 다른 유사 영상에 대해서도 바르게 검색할 수 있으며, 각 특징을 일반화해줌으로 이동.회전.크기 변화에도 불변하는 견고성을 가진다. 또한 효율적인 검색을 위해 2단계의 구조를 사용하였으며, 각 단계마다 계산량을 줄여 검색 시간을 감소시키도록 설계되었다.

• The Journal of the Korea Contents Association
• /
• v.11 no.5
• /
• pp.125-137
• /
• 2011

Recently the research on the system using images taken from camera phones as input is actively conducted. This paper proposed a system that shows wine pictures which are similar to the input wine label in order. For the calculation of the similarity of images, the representative color of each cell of the image, the recognized text color, background color and distribution of feature points are used as the features. In order to calculate the difference of the colors, RGB is converted into CIE-Lab and the feature points are extracted by using Harris Corner Detection Algorithm. The weights of representative color of each cell of image, text color and background color are applied. The image similarity is calculated by normalizing the difference of color similarity and distribution of feature points. After calculating the similarity between the input image and the images in the database, the images in Database are shown in the descent order of the similarity so that the effort of users to search for similar wine labels again from the searched result is reduced.