• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.498-500
• /
• 2015

본 논문에서는 검사 시간과 비용이 적게 드는 초음파 영상에서 결절종을 추출하는 방법을 제안한다. 제안된 방법은 초음파의 영상에서 퍼지 Stretching기법을 적용하여 명암 대비를 증가시킨 후, 8방향 윤곽선 추적 방법을 적용하여 결절종 후보 영역을 추출한다. 결절종이 형태학적으로 타원 형태를 가지는 정보를 이용하여 추출된 결절종 후보 영역에 침식과 팽창 기법을 적용하여 최종적으로 결절종 영역을 추출한다. 제안된 방법을 결절종 초음파 영상을 대상으로 실험한 결과, 결절종 영상에서 결절종 영역이 비교적 정확히 추출되었고 전문의가 결절종의 수술 여부를 분석할 수 있는 정보를 제공할 수 있는 가능성을 확인하였다.

• Korean Journal of Veterinary Research
• /
• v.55 no.1
• /
• pp.47-52
• /
• 2015

The purpose of this study was to determine if contrast media would enhance visualization of the endocardium for assessment of left ventricle (LV) function. In addition, differences between pre- and post-contrast evaluation for the cardiac output measurements including the modified Simpson's method and automated contour tracking (ACT) method were examined. Ten clinically healthy adult beagle dogs (three males and seven females) between 2~3 years old and weighing 6.6~10.8 kg were used. Echocardiographic examinations were performed to compare pre- and post-contrast LV endocardium visualization using a segmental scoring method. Two different methods for measuring cardiac output were also compared. LV visualization was significantly enhanced in post-contrast echocardiography (p < 0.01). Significant differences between pre- and post-contrast measurements for the modified Simpson's method (p < 0.05) were also observed. No significant difference was found for the ACT method. Contrast echocardiography provides better LV chamber opacification and significantly improves wall segment visualization. Furthermore, contrast echocardiography for measuring cardiac output is helpful for the modified Simpson's method.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.341-345
• /
• 2009

We present an augmented reality (AR) application for cell phone where users put a virtual pet on their palms and play/interact with the pet by moving their hands and fingers naturally. The application is fundamentally based on hand/palm pose recognition and finger motion estimation, which is the main concern in this paper. We propose a fast and efficient hand/palm pose recognition method which uses natural features (e.g. direction, width, contour shape of hand region) extracted from a hand image with prior knowledge for hand shape or geometry (e.g. its approximated shape when a palm is open, length ratio between palm width and pal height). We also propose a natural interaction method which recognizes natural motion of fingers such as opening/closing palm based on fingertip tracking. Based on the proposed methods, we developed and tested the AR application on an ultra-mobile PC (UMPC).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.4
• /
• pp.787-795
• /
• 1998

In this paper, we have improved the speed of gradient operation, which needs to calculate Optical Flow for estimating a moving object, and proposed a method which estimate the contour of a moving object by the logical operationg of Optical Flow and edge in noisy images. The proposed method, which recognize to a moving ogject and traking a moving object, using logical operation of Optical Flow and edge in low-level has a advantage that is simpler than the known method for moving objects estimation. In addition, we have simulated several images using method I and method II on improved Gradient operation speed. When we have compared the average value of total operation time, method I is improved with 12% of operation speed compared with the known method, method II is improved with 38% operation speed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.467-471
• /
• 2005

본 논문에서는 명암도 변화 및 윤곽선 추적 알고리즘과 개선된 오류 역전파 알고리즘을 이용한 차량 번호판 인식 방법을 제안한다. 비영업용 차량 영상을 대상으로 차량 번호판 영역을 추출하기 위해 명암도 변화 특성을 이용하여 차량 번호판 영역을 추출한다. 추출된 차량 번호판 영역에 반복 이진화 방법을 적용하여 차량 번호판의 영역을 이진화하고, 이진화된 차량 번호판 영역에 대해서 윤곽선 추적 알고리즘을 적용하여 개별 코드를 추출한다. 추출된 개별 코드 인식은 일반화된 델타 학습 방법에 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하는 개선된 오류 역전파 알고리즘을 적용한다. 제안된 방법의 인식 성능을 평가하기 위하여 실제 비영업용 차량 번호판에 적용한 결과, 기존의 차량 번호판 인식 방법보다 효율적인 것을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.211-213
• /
• 2010

본 논문에서는 형태학적 처리 방법과 8 방향 윤곽선 추적을 이용하여 손금을 추출하는 방법을 제안한다. YCbCr컬러 공간에서 Y:65~255, Cb:25~255, Cr:130~255에 해당되는 피부색 임계치를 이용하여 손 영역을 추출한다. 추출된 손 영역에서 내부 픽셀의 3:1 이상, 전체 영상의 2:1이상인 손의 형태학적 정보와 8 방향 윤곽선 추적 기법을 이용하여 잡음을 제거한다. 잡음이 제거된 손 영상에서 스트레칭 기법과 소벨 마스크를 이용하여 에지를 추출한다. 추출된 에지 영상에서 블록 이진화 기법을 이용하여 이진화한 후에 가로와 세로가 각각 10픽셀 이상이고 20픽셀 이하인 손금의 형태학적 정보를 이용하여 잡음 및 손의 윤곽선을 제외한 손금을 추출한다. 추출된 손금에서 Labeling 기법을 이용하여 개별 손금의 중요선을 추출한다. 핸드폰 카메라에서 획득한 손바닥 영상을 대상으로 실험한 결과, 제안된 방법이 손금 추출에 효율적인 것을 확인할 수 있었다.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.611-624
• /
• 2012

'Gesture' is the most intuitive means of communication except the voice. Therefore, there are many researches for method that controls computer using gesture input to replace the keyboard or mouse. In these researches, the method of user detection and main body parts estimation is one of the very important process. in this paper, we propose user objects detection and main body parts estimation method on inaccurate depth information for pose estimation. we present user detection method using 2D and 3D depth information, so this method robust to changes in lighting and noise and 2D signal processing 1D signals, so mainly suitable for real-time and using the previous object information, so more accurate and robust. Also, we present main body parts estimation method using 2D contour information, 3D depth information, and tracking. The result of an experiment, proposed user detection method is more robust than only using 2D information method and exactly detect object on inaccurate depth information. Also, proposed main body parts estimation method overcome the disadvantage that can't detect main body parts in occlusion area only using 2D contour information and sensitive to changes in illumination or environment using color information.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.35 no.3
• /
• pp.301-311
• /
• 1999

The investigation to evaluate the possible effects of fish behaviour on acoustic target strength was carried out during the 1997 and 1998 hydroacoustic-demersal trawl surveys in the southern waters of Korea.The swimming speed and the target strength of individual, acoustically resolved fished swimming through the sound beam were measured using the split-beam tracking method on board R/V Kaya.The results obtained can be summarized as follows:1. The alongship and athwartship angles between -3dB poionts of a hull mounted 38 kHz split beam tranducer used in these surveys was >$3.76^{\circ}\;and\;6.74^{\circ}$ respectively, and the equal energy contour obtained from the measured beam pattern showed approximately the circular pattern. 2. The swimming speed measured off the south coast of Sorido in 23 January 1997 ranged 0.10 to 0.80 m/s with the average swimming spped of 0.36 m/s, and the target strength ranged -64.8 to -31.7 dB with the average target strength of -52.7 dB. The most dominant species sampled in this survey area were Japanese scaled sardine, Sardinella zunasi and Konoshiro gizzard shad, Konosirus punctatus, respectively.3. The swimming speed measured off the east coast of Kojedo in 24 March 1997 ranged 0.10 to 1.10 m/s with the average swimming speed of 0.40 m/s, and the target strength ranged -64.8 to -51.5 dB with the average target strength of -59.2 dB. The most dominant species sampled in this survey area were Swordtip squid, Photololigo edulis, Konoshiro gizzard shad and Japanese flying squid, Toddarodes pacificus, respectively and the swimming activity of these species seems to be controlled at speeds between 0.20 and 0.60 m/s. 4. The swimming speed measured the south coast of Kojedo in 25 March 1997 ranged 0.10 to 1.40 m/s with the average swimming speed of 0.51 m/s and the target strength ranged -64.3 to -47.7 dB with the average target strength of -55.1 dB. The most dominant species sampled in this survey area were Swordtip squid, Blotchy sillage, Sillago maculata and japanese scaled sardine, respectively and the swimming activity of these species seems to be controlled at speeds between 0.20 and 0.70 m/s.5. The swimming speed measured during morning twilight in the southeastern water of Cheju Island in 11 July 1998 ranged 0.20 to 1.0 m/s with the average swimming speed of 0.53 m/s, and the target strength ranged -65.0 to -47.0 dB with the average target strength of -57.1 dB. The most dominant species sampled in this survey area were Swordtip squid, Black scraper, Thamnaconus modesutus and japanese flying squid, respectively and the tile angle ranged$ +28^{\circ}\;to\;+2^{\circ}$ with the average tilt angle of -8.1$^{\circ}$ showing the downward migration.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.1
• /
• pp.80-87
• /
• 2004

In this paper we proposed the novel feature extraction method that is able to extract the individual characters from the license plate area of the car image more precisely by using the RGB color information and the fuzzy binarization newly proposed. The proposed method, first, extracts from the original image the areas that the pixels with the colors around the green are concentrated on as the candidate areas of the license plate, and selects the area with the most intensive distribution of pixels with the white color among the candidate areas as the license plate area. Second the noises of the license plate area should be removed by using 34{\times}$3 Sobel masking, and the fuzzy binarization method are proposed and applied to the license plate area to generate the binarized image of the license plate area. Lastly, the application of the contour tracking algorithm to the binarized area extracts the individual characters from the license plate area. The experiment on a variety of the real car images showed that the proposed method generates the higher rate of success for character extraction than the previous methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.983-989
• /
• 2006

Current emigration and immigration control inspects passports by the naked eye, registers them by manual input, and compares them with items of database. In this paper, we propose the method to recognize information codes of passports. The proposed passport recognition method extracts character-rows of information codes by applying sobel operator, horizontal smearing, and contour tracking algorithm. The extracted letter-row regions is binarized. After a CDM mask is applied to them in order to recover the individual codes, the individual codes are extracted by applying vertical smearing. The recognizing of individual codes is performed by the RBF network whose hidden layer is applied by ART 2 algorithm and whose learning between the hidden layer and the output layer is applied by a generalized delta learning method. After a photo region is extracted from the reference of the starting point of the extracted character-rows of information codes, that region is verified by the information of luminance, edge, and hue. The verified photo region is certified by the classified features by the ART 2 algorithm. The comparing experiment with real passport images confirmed the good performance of the proposed method.