• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제39권1호
• /
• pp.40-48
• /
• 2002

Three-Dimensional scene reconstruction from images acquired with different viewpoints is possible as estimating Fundamental matrix(F-matrix) that indicates the epipolar geometry of two images. Correspondence points required to calculate F-matrix of two images include noise such as miss matches, so generally it is hard to calculate F-matrix accurately. In this paper, we classify noise into two types; outlier and minute noise. we propose SSOR algorithm that estimate F-matrix effectively. SSOR algorithm is rejecting outlier step by step in a noise environment. To evaluate the performance of proposed algorithm we simulated with synthetic images and real images. As a result of simulation we show that proposed algorithm is better than conventional algorithms.

• Korean Journal of Optics and Photonics
• /
• 제12권1호
• /
• pp.55-60
• /
• 2001

We propose a method to extract features optically from the input pattern by use of an array of Hough transfOllli filters. Here the subparts of the input pattern are Hough-transformed by. their cOlTesponding elements of the filter array independently and simultaneously. Compared with the conventional method, in which the whole input pattern is Hough-transformed by a single optical filter, the proposed method not only provides the improved optical transform results when the input pattern becomes complex but also extracts the approximate position information of the line segment features. To show the feasibility of this approach, we fabricated a $5\times5$ filter array and performed preliminary experiments.iments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국해양정보통신학회 2001년도 춘계종합학술대회
• /
• pp.633-637
• /
• 2001

In this paper, we proposed model creation algorithm for multiple moving objects tracking. The proposed algorithm is divided that the initial model creation step as moving objects are entered into background image and the model reformation step in the moving objects tracking step. In the initial model creation step, the initial model is created by AND operating division image, divided using difference image and clustering method, and edge image of the current image. In the model reformation step, a new model was reformed in the every frame to adapt appearance change of moving objects using Hausdorff Distance and 2D-Logarithmic searching algorithm. We simulated for driving cart in the road. In the result, model was created over 98% in case of irregular approach direction of cars and tracking objects number.

• Journal of Biomedical Engineering Research
• /
• 제15권4호
• /
• pp.419-427
• /
• 1994

A new method of digital image analysis technique for discrimination of cancer cell was presented in this paper. The object image was the Thyroid Gland cells image that was diagnosed as normal and abnormal (two types of abnormal : follicular neoplastic cell, and papillary neoplastic cell), respectively. By using the proposed region segmentation algorithm, the cells were segmented into nucleus. The 16 feature parameters were used to calculate the features of each nucleus. As a consequence of using dominant feature parameters method proposed in this paper, discrimination rate of 91.11 % was obtained for Thyroid Gland cells.

• Journal of the Korea Society of Computer and Information
• /
• 제8권2호
• /
• pp.24-30
• /
• 2003

In this Paper VTQM(Variable Threshold quantization Method) is proposed, which enhances PSNR by composing the advantages of round-off and truncation quantization methods. From vast experiments, PSNR's of JPEG images with the method are compared with that of standard JPEG methods. At the boundary which affects the compression ratio, VTQM quantizes with a new threshold to reduce the length of compressed data; otherwise, VTQM employs the round-off quantization method to preserve the original image information. As a result, VTQM reduces bit rate while preserving the image quality. The experimental results show that VTQM enhances PSNR by 0.2∼0.3dB, 0.4∼0.5dB with the same bit rate than those of the traditional truncation and round-off quantization methods, respectively.

• Journal of the Korea Convergence Society
• /
• 제8권3호
• /
• pp.177-184
• /
• 2017

The purpose of this study was to explore children and robot interaction in distant language learning environments using three different video-conferencing technologies-two traditional screen-based videoconference technologies and a telepresence robot. One American and six Korean elementary school students participated in our case study. We relied on narratives of one-on-one interviews and observation of nonverbal cues in robot assisted language learning. Our findings suggest that participants responded more positively to interactions via a telepresence robot than to two screen-based video-conferencings, with many citing a stronger sense of immediacy during robot-mediated communications.

• The KIPS Transactions:PartB
• /
• 제16B권2호
• /
• pp.165-172
• /
• 2009

According to the American Cancer Society, breast cancer is the second largest cause of cancer deaths and most frequently diagnosed cancer in women. The currently most popular method for early detection of breast cancer is the digital mammography. A mass or calcification lesion has been known as the most important clue for the diagnosis. In this paper, we propose a diagnosis approach based on fuzzy cluster knowledge base. We combine different two sources of feature data in duel OFUN-NET and produce the diagnosis result with possibility degree. We also present the experimental results on the dataset of mass and calcification lesions extracted from the public real world mammogram database DDSM. These results show higher classification accuracy than conventional methods and the feasibility as a decision supporting tool for diagnosis of digital mammogram.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• 제41권5호
• /
• pp.33-40
• /
• 2004

In this paper, we constructs face database by using wavelet comparison, and compare face recognition rate by using principle component analysis (Principal Component Analysis : PCA) algorithm. General face recognition method constructs database, and do face recognition by using normalized size. Proposed method changes image of normalized size (92${\times}$112) to 1 step, 2 step, 3 steps to wavelet compression and construct database. Input image did compression by wavelet and a face recognition experiment by PCA algorithm. As well as method that is proposed through an experiment reduces existing face image's information, the processing speed improved. Also, original image of proposed method showed recognition rate about 99.05%, 1 step 99.05%, 2 step 98.93%, 3 steps 98.54%, and showed that is possible to do face recognition constructing face database of large quantity.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1383-1385
• /
• 1996

A network based interactive magnetic resonance imaging (MRI) system has been developed using the World Wide Web. For this purpose, an HTTP server is developed on the host computer of the MRI system. Capabilities of video and audio conferencing are included for monitoring experiment. Using the developed system. MRI imaging has been successfully carried out at the Signal Processing Lab in the Kwangwoon University with the remote MRI system located at the Medical Image Research Center at the KAIST in Daejon.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국해양정보통신학회 2010년도 춘계학술대회
• /
• pp.193-196
• /
• 2010

In this paper, we propose a method to classify the types of vehicle as full, medium, or small size. The proposed method is composed of three steps. First, after obtaining vehicle contour from template candidate image, edge distance template is created by distance transform of the vehicle's contour. Second, the vehicle type of input image is classified as the type of template which has minimal edge distance with input image. The edge distance value means the measurement of distance between input image and template at each pixel which is part of vehicle contour. Experimental results demonstrate that our method presented a good performance of 80% about test images.