• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.2
• /
• pp.178-186
• /
• 2003

Recently, many researchers have been interested in biometric systems such as fingerprint, handwriting, key-stroke patterns and human iris. From the viewpoint of reliability and robustness, iris recognition is the most attractive biometric system. Moreover, the iris recognition system is a comfortable biometric system, since the video image of an eye can be taken at a distance. In this paper, we discuss human iris recognition, which is based on accurate iris localization, robust feature extraction, and Neural Network classification. The iris region is accurately localized in the eye image using a multiresolution active snake model. For the feature representation, the localized iris image is decomposed using wavelet transform based on dyadic Haar wavelet. Experimental results show the usefulness of wavelet transform in comparison to conventional Gabor transform. In addition, we present a new method for setting initial weight vectors in competitive learning. The proposed initialization method yields better accuracy than the conventional method.

• Annual Conference on Human and Language Technology
• /
• 1990.11a
• /
• pp.200-207
• /
• 1990

본 논문은 다양한 활자체 및 크기의 한글 문자 영상에서의 정보량 및 엔트로피의 분포에 관한 연구이다. 12 종류의 서로 다른 활자체 및 크기의 한글 문자 영상이 실험에 사용되었으며, 사용 빈도수가 높은 520 자의 한글 문자 영상에 대하여 정보량과 엔트로피를 측정하였다. 실험 결과의 분석을 통하여 정보량과 엔트로피의 측정치는 문자의 구조적 형태에 따라 변하지만 활자체에는 무관하며, 대부분의 정보량이 문자의 가장자리 부분에 위치함을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.593-596
• /
• 2001

본 논문에서는 획기반 필기한글 문자분할 방법을 제안하고 이를 한글단어인식에 적용하였다. 제안된 방법에서는 획 단위의 문자분할을 시도함으로써 불필요한 분할점을 줄일 수 있었을 뿐 아니라 문자간 획의 접촉이나 겹침을 해결할 수 있었다. 실험에서는 이를 단어인식에 적용하여 비교적 높은 인식률을 얻음으로써 제안된 방법의 가능성을 입증하였다. 실험에서 이용한 문자인식기의 성능이 낮음에도 불구하고 비교적 높은 단어인식률을 얻을 수 있었던 것은 의미 있는 획 단위의 문자분할을 통해 불필요한 분할 가능성을 줄였고, 단어사전을 이용함으로써 사전정보를 충분히 활용할 수 있었기 때문이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.346-349
• /
• 2019

본 연구를 통해 당구를 처음 접하는 사람들이 혼자서도 올바른 스트로크 자세를 연습할 수 있도록 하기 위한 시스템을 설계하였다. 6 축 자이로 센서를 활용하여 가속도, 각속도 센서 값을 안드로이드와 BLE 통신으로 수집하고 그 값으로 스트로크의 속도와 각도, 방향을 계산하여 유사율을 나타낸다. 또한 터치센서에 스트로크 시에 타격감을 주기 위하여 모바일의 진동을 울려주며, 센서에 터치 된 값을 이용하여 사용자가 실제 타격한 당구공의 타점을 모바일에서 실시간으로 보여준다. 동시에 앞서 계산된 유사율을 그래프와 수치상으로 확인할 수 있다. 모범 자세와 비교한 피드백을 통하여 올바른 스트로크 자세를 익힐 수 있도록 도와준다.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.667-674
• /
• 2004

Extraction of texts from images is a fundamental and important problem to understand the images. This paper suggests a text region verification method by statistical means of stroke features of the characters. The method extracts 36 dimensional features from $16\times16$sized text and non-text images using wavelet transform - these 36 dimensional features express stroke and direction of characters - and select 12 sub-features out of 36 dimensional features which yield adequate separation between classes. After selecting the features, SVM trains the selected features. For the verification of the text region, each $16\times16$image block is scanned and classified as text or non-text. Then, the text region is finally decided as text region or non-text region. The proposed method is able to verify text regions which can hardly be distin guished.

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.19-26
• /
• 2013

In the Malaysian license plates, alphabets and numerals which are made by plastic, are adhered to a frame as embossing style and occasionally characters in horizontal, vertical directions are aligned with narrow space. So the extraction of character stroke information can be hard in the vehicle images of low illumination intensity. In this paper, Malaysian license plate recognition algorithm for low illumination intensity image is proposed. DoG filtering based character stroke generation method is introduced to derive exact connected components of strokes in the vehicle image of low illumination intensity. After localization of plate by connected component analysis, characters are segmented and recognized. Algorithm is experimented for the 6,046 vehicle images captured in Kuala Lumpur by IR camera without using any special light during day and night. The experimental results show that recognition accuracy of plates is 96.1%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.11
• /
• pp.1175-1184
• /
• 1992

A new classification method and recognition algorithms for printed Korean and Chinese character is studied for Korean text which contains both Korean and Chinese characters. The proposed method utilizes structural features of the vertical and horizontal vowel in Korean character. Korean characters are classified into 6 groups. Vowel and consonant are separated by means of different vowel extraction methods applied to each group. Time consuming thinning process is excluded. A modified crossing distance feature is measured to recognize extracted consonant. For Chinese character, an average of stroke crossing number is calculated on every characters, which allows the characters to be classified into several groups. A recognition process is then followed in terms of the stroke crossing number and the black dot rate of character. Classification between Korean and Chinese character was at the rate of 90.5%, and classification rate of Ming-style 2512 Korean characters was 90.0%. The recognition algorithm was applied on 1278 characters. The recognition rate was 92.2%. The densest class after classification of 4585 Chinese characters was found to contain only 124 characters, only 1/40 of total numbers. The recognition rate was 89.2%.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.475-486
• /
• 2020

This paper is a thesis on media art technology for high-tech performances and exhibitions. After creating an interactive stroke in VR, it is projected in real time through a media facade technique. Among our traditional dramas emphasizing linear movements, movements were extracted from the Bongsan mask dance, and the movements of the lines were used in a media art performance called 'Multi-face Convergence'. When motion data enters the virtual space, geometry consisting of faces is created in the VR space. The created strokes can be set with various brush types, and when performing, a stroke with a red fire effect that matches a dynamic movement was used. It was made to be able to harmonize with the dancers performing the Bongsan mask dance. The medium called VR has characteristics that are not suitable for melting into a performance, but in this performance, it has overcome its limitations by using a technique called media façade. We propose the world's first performance technique that combines interactive strokes with traditional dance performances.

• The Korean Journal of Physiology
• /
• v.21 no.2
• /
• pp.305-311
• /
• 1987

To evaluate training effect, the step exercise was loaded to three mem for nine weeks. Step score, cardiopulmonary functions and blood constituents were measured before, during and after the test exercise (50 cm-step exercise and treadmill running), and were compared with the pre-tranining values. The results were as follows: 1) By the training, Harvard step score increased remarkably, expecially in the early stage of training. 2) The post-training values of maximal oxygen uptake increased very significantly and it seemed to be due to increases of stroke volume and tissue oxygen extraction. 3) After the training, the degree of increase in expired volume was small during the treadmill exercise. 4) By the training, increasing rate of respiratory quotient lessened during the exercise and it was considered to be caused by the decreases of carbohydrate consumption and anaerobic metabolism. 5) The blood cholesterol concentrations were harldy changed with this degree of training. 6) The blood lactate level decreased during the recovery periods and the values of the recovery 0 and 5 minutes decreased remarkably, in comparison with the pre-trained values. The above results suggest that the 9 week-training of the step exercise brings about the enhancement of circulatory functions and tissue oxygen utilization, and changes of food-stuffs used during the exercise.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.9
• /
• pp.2312-2325
• /
• 2013

In this paper, we propose a preprocessing method that it is to correct the distortion of text area in Korean signboard images as a preprocessing step to improve character recognition. Distorted perspective in recognizing of Korean signboard text may cause of the low recognition rate. The proposed method consists of four main steps and eight sub-steps: main step consists of potential vertical components detection, vertical components detection, text-boundary estimation and distortion correction. First, potential vertical line components detection consists of four steps, including edge detection for each connected component, pixel distance normalization in the edge, dominant-point detection in the edge and removal of horizontal components. Second, vertical line components detection is composed of removal of diagonal components and extraction of vertical line components. Third, the outline estimation step is composed of the left and right boundary line detection. Finally, distortion of the text image is corrected by bilinear transformation based on the estimated outline. We compared the changes in recognition rates of OCR before and after applying the proposed algorithm. The recognition rate of the distortion corrected signboard images is 29.63% and 21.9% higher at the character and the text unit than those of the original images.