• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.145-148
• /
• 2002

우리가 원하는 고수준의 검색 개념을 영상에서의 저수준 특징들을 조합하여 표현하는 데는 한계가 있다. 한편, 우리의 검색 개념은 주로 영상에 포함된 객체 단위로 형성되는 것이 일반적이다. 본 논문에서는 영상의 중심 부근에 비교적 큰 크기로 정의되는 중심 객체 및 중심 객체주변의 배경 영역을 추출하여 검색에 활용함으로써, 인간의 검색 의지를 최대한 정확하게 반영할 수 있는 하나의 방법을 제안한다. 중심 객체와 배경 영역은 영상분할 및 영역병합 결과에서 영상의 중앙 및 모서리에 존재하는 영역을 선정하여 칼라 유사도를 기준으로 영역확장을 통해 구한다. 검색은 단계적으로 할 수 있도록 하였는데, 먼저 사용자의 키워드에 의한 검색이 가능하도록 하였으며, 검색 결과는 그룹핑에 의한 대표영상을 보여 준 후 사용자가 원하는 영상을 선택적으로 얻을 수 있도록 하였다. 아울러, 하나 이상의 영상에서 추출된 객체와 배경을 조합하여 재검색할 수 있도록 함으로써 검색 성능을 높이고자 하였다. 한편, 자동 추출된 객체를 이용하여 사용자가 객체 영역을 지정하기 위해 개입하는 번거로움을 줄이면서도 사용자가 영역을 직접 선택한 경우와 비슷한 결과를 얻을 수 있도록 하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.281-282
• /
• 2008

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.377-380
• /
• 2003

A new color image segmentation scheme is presented in this paper. The proposed algorithm consists of image simplification, region labeling and color clustering. The vector-valued diffusion process is performed in the perceptually uniform LUV color space. We present a discrete 3-D diffusion model for easy implementation. The statistical characteristics of each labeled region are employed to estimate the number of total clusters and agglomerative hierarchical clustering is performed with the estimated number of clusters. Since the proposed clustering algorithm counts each region as a unit, it does not generate oversegmentation along region boundaries.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.569-572
• /
• 1999

In this paper we present a color image segmentation algorithm based on statistical models. A novel deterministic annealing Expectation Maximization(EM) formula is derived to estimate the parameters of the Gaussian Mixture Model(GMM) which represents the multi-colored objects statistically. The experimental results show that the proposed deterministic annealing EM is a global optimal solution for the ML parameter estimation and the image field is segmented efficiently by using the parameter estimates.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.538-540
• /
• 1998

본 논문은 고개를 상/하로 끄덕이거나 좌/우로 가로 저어서 긍정과 부정을 구별하기 위한 것이다. 다시 말해서, 마우스나 키보드 대신에 머리의 움직임을 사용해서 '예/아니오'를 인식한다. 본 논문에서는 정규화된 칼라 공간(chromatic color space)과 조도(illumination)를 이용하여 얼굴 영역을 찾고 분할하는 자동 얼굴 영역 찾기와 영상차의 위치 비교와 움직임 량을 이용하여 우선 순위를 갖는 단순한 방향성을 구별하는 자동 의사 인식의 두 단계로 구성되어 있다. 이러한 단순한 방향성의 조합으로 '예/아니오'를 구분한다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.936-946
• /
• 2009

A graph cuts method has recently attracted a lot of attentions for image segmentation, as it can globally minimize energy functions composed of data term that reflects how each pixel fits into prior information for each class and smoothness term that penalizes discontinuities between neighboring pixels. In previous approaches to graph cuts-based automatic image segmentation, GMM(Gaussian mixture models) is generally used, and means and covariance matrixes calculated by EM algorithm were used as prior information for each cluster. However, it is practicable only for clusters with a hyper-spherical or hyper-ellipsoidal shape, as the cluster was represented based on the covariance matrix centered on the mean. For arbitrary-shaped clusters, this paper proposes graph cuts-based image segmentation using mean shift analysis. As a prior information to estimate the data term, we use the set of mean trajectories toward each mode from initial means randomly selected in $L^*u^*{\upsilon}^*$ color space. Since the mean shift procedure requires many computational times, we transform features in continuous feature space into 3D discrete grid, and use 3D kernel based on the first moment in the grid, which are needed to move the means to modes. In the experiments, we investigate the problems of mean shift-based and normalized cuts-based image segmentation methods that are recently popular methods, and the proposed method showed better performance than previous two methods and graph cuts-based automatic image segmentation using GMM on Berkeley segmentation dataset.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.4
• /
• pp.89-97
• /
• 2015

In this paper, a method of color image segmentation based on DBSCAN(Density Based Spatial Clustering of Applications with Noise) using compactness of superpixels and texture information is presented. The DBSCAN algorithm can generate clusters in large data sets by looking at the local density of data samples, using only two input parameters which called minimum number of data and distance of neighborhood data. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. Each superpixel is consist of pixels with similar features such as luminance, color, textures etc. Superpixels are more efficient than pixels in case of large scale image processing. In this paper, superpixels are generated by SLIC(simple linear iterative clustering) as known popular. Superpixel characteristics are described by compactness, uniformity, boundary precision and recall. The compactness is important features to depict superpixel characteristics. Each superpixel is represented by Lab color spaces, compactness and texture information. DBSCAN clustering method applied to these feature spaces to segment a color image. To evaluate the performance of the proposed method, computer simulation is carried out to several outdoor images. The experimental results show that the proposed algorithm can provide good segmentation results on various images.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.1-12
• /
• 2009

The correct detection of skin color is an important preliminary process in fields of face detection and human motion analysis. It is generally performed by three steps: transforming the pixel color to a non-RGB color space, dropping the illuminance component of skin color, and classifying the pixels by the skin color distribution model. Skin detection depends on by various factors such as color space, presence of the illumination, skin modeling method. In this paper we propose a 3d skin color model that can segment pixels with several ethnic skin color from images with various illumination condition and complicated backgrounds. This proposed skin color model are formed with each components(Y, Cb, Cr) which transform pixel color to YCbCr color space. In order to segment the skin color of several ethnic groups together, we first create the skin color model of each ethnic group, and then merge the skin color model using its skin color probability. Further, proposed model makes several steps of skin color areas that can help to classify proper skin color areas using small training data.

• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.593-601
• /
• 2016

This paper is related to the Region-based Spectral Correlation Estimation(RSCE) coding method that makes it possible to achieve the high-compression ratio by estimating color component images from luminance image. The proposed method is composed of three steps. First, Y/C bit-plane summation image is defined using normalized chrominance summation image and luminance image, and then the Y/C bit-plane summation image is segmented for extracting the shape information of the regions. Secondly, the scale factor and the offset factor minimizing the approximation square errors between luminance image and R, B images by the each region are calculated. Finally, the scale factor and the offset factor for the each region are encoded into bit stream. Referring to the results of computer simulation, the proposed method provides more than two or three times higher compression ratio than JPEG/Baseline or JPEG2000/EBCOT algorithm in terms of bpp needed for encoding two color component images with the same PSNR.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.223-226
• /
• 2003

When we detect side-view face in color image, we decide a candidate face region using skin-tone color, and confirm to the face by template matching. Cang Wei use a left and a right template of face, calculate to similarity value by hausdorff method, and decide the final side-view face. It has a characteristic that side-view face is wide spreading neck region. To get exactly result, face region is separated vertically by 3 pixel unit, and matched template. In this paper, we assume that a side-view face is a right side-view or a left side-view face. We separate a half of the candidate face region vertically, and regard a left side as left candidate face, a right side as right candidate face by template matching. This method detect faster than Gang Wei method.