• The Transactions of the Korea Information Processing Society
• /
• v.4 no.4
• /
• pp.1132-1140
• /
• 1997

In many vision tasks of the major obstacles is the specular highkight of smoth objects, which causes a misinterpretation of objects.This paper presents an dffcient algorithm for highight detection and object reconstruction, blsed on the theory of photometric stereo in which the location of highilight changes as the position of illumination source changes.Two images, referred to as base image and reference image.are sequentially taken with two different positionhs of the two images.The difference image is thresholded to detct the specular spike of the highlight.Then the specu-lar lobe around the specular spike is detected to reconstruct the object.The proposed algorithm can be applied to metals and dielectrics, regardlless of the surface chracteristics.This method can also be aplied to the case when the background is brighter than the object.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2555-2564
• /
• 2000

In this paper, a new unsupervised image segmentation algorithm is proposed. To model the contextual information presented in images, the characteristics of the Markov random fields (MRF) are utilized. Textured images are modeled as realizations of the stationary Gaussian MRF on a two-dimensional square lattice using the conditional autoregressive (CAR) equations with a second-order noncausal neighborhood. To detect boundaries, hypothesis tests over two masked areas are performed. Under the hypothesis, masked areas are assumed to belong to the same class of textures and CAR equation parameters are estimated in a minimum-mean-square-error (MMSE) sense. If the hypothesis is rejected, a measure of dissimilarity between two areas is accumulated on the rejected area. This approach produces potential edge maps. Using these maps, boundary detection can be performed, which resulting no micro edges. The performance of the proposed algorithm is evaluated by some experiments using real images as weB as synthetic ones. The experiments demonstrate that the proposed algorithm can produce satisfactorY segmentation without any a priori information.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.2
• /
• pp.69-77
• /
• 1993

Investigation is given to the detailed procedure of a computer assisted automatic correction for scanning errors of the digital images of close-range photographs scanned by the CCD camera scanner. After determination of the exterior orientation parameters, photo coordinates of the all pixels were calculated using collinearity equation. For the generation of geometric corrected image from the photo coordinates of the all pixels, inverse-weighted-distance average method was used. And the accuracy of the resulting new image was checked comparing its image coordinates with there corresponding ground coordinates for the check points.

• Korean Journal of Food Science and Technology
• /
• v.30 no.3
• /
• pp.473-479
• /
• 1998

Identification of rice species was attempted by three side (top, side and front) images of brown rice. Nine parameters of each image were area, aspect ratio, maximum diameter, minimum diameter, perimeter, roundness and red (R), green (G) and blue (B) pixel values of an image. Forty rice samples consisted of 19 species used for the study and total 27 image characteristics for a kernel were measured. For calibration and confirmation, 105 and 20 brown rice kernels per each sample were used respectively. For best identification of rice species, 24 image characteristics were selected for discriminant analysis. Average percentages for correct identification of rice species were 84.75% and 84.93% for calibration and confirmation data set, respectively. The highest and lowest percentage for correct identification were 99.05% for Nongan and 50.63% for Hwaseung respectively in calibration data. The confirmation data showed that the correct identification of Nongan or Paalgong was 100%, while that of Hwaseung was 47.62%. The result of the study showed that three side (top, side and front) image of brown rice was not suitable for identification of rice species suggesting that additional techniques are required for better discrimination of rice species.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.95-98
• /
• 1994

자연발화상에 포함되어, 음성언어 인식에 장애를 초래하는 간투사의 음성적 특성 중 가장 뚜렷이 구별되는 길이특성얼 분석하여 음성언어 인식에 도움을 주는 것을 목적으로 한다. 이 연구에서는 간투사의 대부분을 차지하는 단음절 단일 간투사에 한정하여, 실제 대화의 녹음자료에서 나타나는 간투사의 빈도수와, 그 길이특성을 신분별, 성별, 간투사 유형별로 분석하였다. 또 간투사를 위치에 따라, 음운구초 간투사, 음운구말 간투사로 나누고, 그 길이를 음절 평균, 음운 구초 음절이나 음운구말 음절의 길이와 비교하여 간투사의 증가율을 측정하였다. 분석결과 가장 높은 빈도수를 보이는 단음절 단일 간투사는 어 이며, 간투사 길이 증가율은, 음절평균에 대해서는 그가, 음운구초 평균에 대해서는 응이 가장 큰 증가율을 나타낸다. 전체적을 음운구초 음절길이에 대한 간투사 길이 증가율이 음절평균 길이에 대한 간투사 길이 증가율보다 더 크게 나타났다. 이러한 분석결과를 통해 하위레벨에서 제거할 수 있는 간투사와, 통사적 또는 의미론적 분석이 필요한 상위레벨에서 처리해야할 간투사를 구별할 수 있다. 이와 같은 길이 특성외에 간투사에 대한 다양한 음성적 특성과, 다음절 단일 간투사와, 이중 간투사에 대한 연구가 진척된다면 음성언어 인식에 장애가 되는 간투사의 효과적 배제가 가능할 것으로 보인다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.51-57
• /
• 2023

Smart mirror is an IoT device that attaches a display and an embedded computer to the mirror and provides various information to the user along with the mirror function. This paper presents performance evaluation of the CoMirror system as an extension of the previous research in which proposed and implemented the CoMirror system that connects Smart Mirrors using a network. First, the login performance utilizing face recognition was evaluated. As result of the performance evaluation, it was concluded that the 40 face images are most suitable for face learning and only one face image is most suitable for face recognition for login. Second, as a result of evaluating the message transmission time, the average time was 0.5 seconds for text, 0.63 seconds for audio, and 2.9 seconds for images. Third, as a result of measuring a video communication performance, the average setup time for video communication was 1.8 seconds and the average video reception time was 1.9 seconds. Finally, according to the performance evaluation results, we conclude that the CoMirror system has high practicality.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.2120-2124
• /
• 2007

본 연구에서는 천해역에서 수평 방향으로 방류되는 비부력 원형 난류제트에 대한 수리모형실험을 수행하여, 파랑이 제트의 확산에 미치는 영향을 검토하였다. 수리모형실험시 대상 파랑은 진폭이 작은 규칙파를 적용하였으며, 난류제트의 순간적인 유속장은 입자화상유속계(particle image velocimetry, PIV)기법을 이용하여 측정하였다. 평균유속장은 PIV기법으로 측정된 순간유속장을 위상평균하여 계산하였으며, 파의 진폭을 변화시키며 실험을 수행하였고, 파의 진폭변화에 따른 제트의 유속분포로부터 제트의 중심선과 제트단면을 추정하였다. 제트의 중심선속도는 파의 진폭이 증가함에 따라 중심선속도의 감소 시점이 빨라졌으며, 제트의 횡단면분포의 고유특성인 자기상사성(self-similarity)이 단계적으로 사라졌다. 제트 중심선의 속도와 제트 유속 단면은 제트의 확산정도를 알 수 있는 중요한 인자로서 파랑 진폭의 크기에 따른 이들 인자의 변화로부터 파랑의 분산이 난류제트의 확산현상에 미치는 영향을 알 수 있었다.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.54-66
• /
• 1997

Efficient retrieval of image data is an important research issue in multimedia database. This paper proposes a new approach to a content-based image retrieval which allows queries to be composed of the local texture patterns and the slope components of contour points. The texture patterns extracted from the source image using the graylevel co-occurrence matrix and the slope components of contour points extracted from the binary image are converted into a internal feature representation of reduced dimensionality which preserves the perceptual similarity and those features can be used in creating efficient indexing structures for a content-based image retrieval. Experimental results of the image retrievalare presented to illustrate the usefulness of this approach that demonstrates the precision 82%, the recall 87% and the average rang 3.3 in content-based image data retrieval.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.4C
• /
• pp.533-540
• /
• 2004

This paper proposes a new multispectral image data compression algorithm that can efficiently reduce spatial and spectral redundancies by applying classified prediction, a Karhunen-Loeve transform (KLT), and the three-dimensional set partitioning in hierarchical trees (3-D SPIHT) algorithm in the wavelet transform (WT) domain. The classification is performed in the WT domain to exploit the interband classified dependency, while the resulting class information is used for the interband prediction. The residual image data on the prediction errors between the original image data and the predicted image data is decorrelated by a KLT. Finally, the 3-D SPIHT algorithm is used to encode the transformed coefficients listed in a descending order spatially and spectrally as a result of the WT and KLT. Simulation results showed that the reconstructed images after using the proposed algorithm exhibited a better quality and higher compression ratio than those using conventional algorithms.

• KSBB Journal
• /
• v.16 no.3
• /
• pp.302-306
• /
• 2001

The possibility of biomaterials prepared from natural polymer as a skin substitute was evaluated by measuring biocompatibility. Biodegradable films were prepared by solution blend method in the weight ratio of chitosan for the purpose of useful biomaterials. These films were inserted in the back of rat and their biodegradability was investigated by the film weight and hematology as a function of time for the biotransformation. The result of rat test showed that medium, high viscosity chitosan induced some suspects of inbiocompatibililty in the tissue by foreign body reaction 48 and 72 hours after implantation. Also, we prepared the official burn ointment which is made by low viscosity chitosan. This burn ointment was covered on the skin wound of artificial burn and their effect of healing was investigated by the evaluation of the naked eye and hematological change as a function of time. The result of rats test showed that burn ointments made from chitosan was effective reduction of inflammation than negative group.