• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.631-633
• /
• 2002

본 논문은 대용량 클러스터 기반의 웹 서버 상에서 새로운 내용 기반 부하 분산 기법을 제안한다. 제안된 기법은 웹 서버 로그의 URL 항목에 해시 함수를 적용하여 얻어지는 해시 값에 요청 빈도와 전송될 과일 크기를 누적하여 히스토그램을 생성한다. 그 결과로 생성된 히스토그램의 누적 분포에 히스토그램 균등화 변환함수를 적용하여 각각의 서버 노드에 해시 값에 따라 분포하는 부하를 균등하게 할당할 수 있다. 제안된 부하 분산 기법의 효율성 검증을 위한 시뮬레이션에서 히스토그램 균등화 기법은 서버의 지역적인 캐시 활용과 부하의 균등분산 등의 장점으로 우수한 성능을 나타냄을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.369-372
• /
• 2002

본 논문은 대용량 클러스터 기반의 웹 서버를 위한 새로운 내용 기반 부하 분산 기법을 제안한다. 제안된 기법은 웹 서버 로그의 URL 항목에 해시 함수를 적용하여 얻어지는 해시 값에 요청 빈도와 전송될 파일 크기를 누적하여 히스토그램을 생성한다. 그 결과로 생성된 히스토그램의 누적 분포에 히스토그램 균등화 변환함수를 적용하여 각각의 서버 노드에 해시 값에 따라 분포하는 부하를 균등하게 할당할 수 있다. 제안된 부하 분산 기법의 효율성 검증을 위한 시뮬레이션에서 히스토그램 균등화 기법은 서버의 지역적인 캐시 활용과 부하의 균등 분산 등의 장점으로 우수한 성능을 나타냄을 보인다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.46 no.1
• /
• pp.10-21
• /
• 2009

In order to enhance the contrast in the regions where the pixels have similar intensities, this paper presents a new histogram equalization scheme. Conventional global equalization schemes over-equalizes those regions so that too bright or dark pixels are resulted and local equalization schemes produce unexpected discontinuities at the boundaries of the blocks. The proposed algorithm segments the original histogram into sub-histograms with reference to brightness level and equalizes each sub-histogram with the limited extents of equalization considering its mean and variance. The final image is determined as the weighted sum of the equalized images obtained by using the sub-histogram equalizations. By limiting the maximum and minimum ranges of equalization operations on individual sub-histograms, the over-equalization effect is eliminated. Also the result image does not miss feature information in low density histogram region since the remaining these area is applied separating equalization. This paper includes how to determine the segmentation points in the histogram. The proposed algorithm has been tested with more than 100 images having various contrast in the images and the results are compared to the conventional approaches to show its superiority.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.4
• /
• pp.321-327
• /
• 2015

In this paper, we propose an algorithm for achieving robust Visual Voice Activity Detection (VVAD) for enhanced speech recognition. In conventional VVAD algorithms, the motion of lip region is found by applying an optical flow or Chaos inspired measures for detecting visual speech frames. The optical flow-based VVAD is difficult to be adopted to driving scenarios due to its computational complexity. While invariant to illumination changes, Chaos theory based VVAD method is sensitive to motion translations caused by driver's head movements. The proposed Local Variance Histogram (LVH) is robust to the pixel intensity changes from both illumination change and translation change. Hence, for improved performance in environmental changes, we adopt the novel threshold estimation using total variance change. In the experimental results, the proposed VVAD algorithm achieves robustness in various driving situations.

• Journal of KIISE:Databases
• /
• v.30 no.5
• /
• pp.464-475
• /
• 2003

few sample objects and compressed histogram information of image databases. The histogram information is used to estimate the selectivity of spherical range queries and a small number of sample objects is used to compensate the selectivity error due to the difference of the similarity measures between meta server and local image databases. An extensive experiment on a large number of image data demonstrates that our proposed method performs well in the distributed heterogeneous environment.

• Journal of the Korean Geographical Society
• /
• v.41 no.2 s.113
• /
• pp.139-149
• /
• 2006

Earlier research works focused on the seasonal patterns and bio-geochemical processes in sand dunes, and the satellite data and aerial photographs have been used only as a backdrop or for the multi-temporal delineation of sand dune area. In order to find the optimal way to extract features' characteristics, Gimnyeong sand dune area was selected as a study site. Field works have been carried out three times to collect ground control points and sand samples for laboratory analyses. The texture of sand dune is classified as fine sand, which has been derived from shell fragments. The sand dune penetrated into the island from northwest to southeast direction. An aerial photograph was re-sampled into one-meter resolution and rectified with software including Erdas Imagine and ENVI. Sub-scenes were chosen as samples for sand dune, urban area and rural area. K-group non-parametric analysis had been done for the geometric and spectral values of enclosed texture patches. Urban areas proved to have significant smaller patches than the others.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.133-138
• /
• 2010

In this paper, we make up a feature image including spatial properties and statistical properties on image, and format covariance matrices using region variance magnitudes. By using it to texture classification, this paper puts a proposal for tough texture classification way to illumination, noise and rotation. Also we offer a way to minimalize performance time of texture classification using integral image expressing middle image for fast calculation of region sum. To estimate performance evaluation of proposed way, this paper use a Brodatz texture image, and so conduct a noise addition and histogram specification and create rotation image. And then we conduct an experiment and get better performance over 96%.

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.186-195
• /
• 2016

This paper proposes a vehicle license plate detection method in real road environments using 8 bit-MCT features and a landmark-based Adaboost method. The proposed method allows identification of the potential license plate region, and generates a saliency map that presents the license plate's location probability based on the Adaboost classification score. The candidate regions whose scores are higher than the given threshold are chosen from the saliency map. Each candidate region is adjusted by the local image variance and verified by the SVM and the histograms of the 8bit-MCT features. The proposed method achieves a detection accuracy of 85% from various road images in Korea and Europe.

• The Journal of Engineering Geology
• /
• v.26 no.1
• /
• pp.71-78
• /
• 2016

This study aimed to evaluate the occurrence of natural radionuclides in Korean groundwater. Groundwater radionuclide data for the period 2000-2011 were obtained from the National Institute of Environmental Research and published literature, classified into five groups according to host rock type, and used to construct detailed concentration maps. Radon, uranium, gross-α, and radium concentrations ranged from 0.4 to 64,688.0 pCi/L (mean: 4,907 pCi/L), 0 to 2,297 μg/L (mean: 27.5 μg/L), 0 to 312 pCi/L (mean: 3.9 pCi/L), and 0 to 17.4 pCi/L (mean: 0.2 pCi/L), respectively. Radon concentrations in 562 of a total 1,501 wells (i.e., 53.5%) exceeded 4,000 pCi/L, which is the acceptable contamination threshold established by the United States Environmental Protection Agency. Uranium, gross-α, and radium concentrations exceeded the respective thresholds of 30 μg/L, 15 pCi/L, and 5 pCi/L in 121 of 1,031 wells (11.9%), 34 of 978 wells (3.5%), and 4 of 89 wells (4.5%), respectively. The mean radionuclide concentration in groundwaters hosted by igneous and metamorphic rocks was higher than that in groundwaters hosted by other rock types, such as volcanics, carbonates, and other sedimentary rocks. The correlations between individual radionuclides were weak or insignificant.