• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.700-707
• /
• 2013

In this paper, we propose a non-rigid registration method of lung parenchyma in temporal chest CT scans using region binarization modeling and locally deformable model. To cope with intensity differences between CT scans, we segment the lung vessel and parenchyma in each scan and perform binarization modeling. Then, we match them without referring any intensity information. We globally align two lung surfaces. Then, locally deformable transformation model is developed for the subsequent non-rigid registration. Subtracted quantification results after non-rigid registration are visualized by pre-defined color map. Experimental results showed that proposed registration method correctly aligned lung parenchyma in the full inspiration and expiration CT images for ten patients. Our non-rigid lung registration method may be useful for the assessment of various lung diseases by providing intuitive color-coded information of quantification results about lung parenchyma.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.57-63
• /
• 2009

The rapid growth of computer-based image database, necessity of a system that can manage an image information is increasing. This paper presents a region-based image retrieval method using the combination of color(autocorrelogram), texture(CWT moments) and shape(Hu invariant moments) features. As a color feature, a color autocorrelogram is chosen by extracting from the hue and saturation components of a color image(HSV). As a texture, shape and position feature are extracted from the value component. For efficient similarity confutation, the extracted features(color autocorrelogram, Hu invariant moments, and CWT moments) are combined and then precision and recall are measured. Experiment results for Corel and VisTex DBs show that the proposed image retrieval algorithm has 94.8% Precision, 90.7% recall and can successfully apply to image retrieval system.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.758-761
• /
• 2003

금석문의 영상데이터를 디지털 형태로 검출하고, 영상신호처리 알고리즘을 사용하여 신호의 특성을 분석하고 그 결과를 제시하였다. 대상체는 비석에 음각된 문자로 하였다. 대전 주변의 백제권에서 몇몇 유형의 음각 문자를 형태별로 분류하여 디지털 이미지화한 다음, 문자가 각인된 정보영역과 바탕영역의 신호패턴을 추출하였다. 먼저 칼라 이미지를 grey tone으로 변환한 후, 전처리 과정을 거쳐 이미지의 노이즈나 불명확성을 제거하고 히스토그램 전 영역에 걸쳐 스케일 확장시켰다. 문자가 각인된 정보영역과 바탕영역을 구분하여 무작위로 소이미지 샘플을 취득하고 각 소이미지의 신호패턴을 분석하였다. 그 결과를 중첩의 원리를 이용하여 합성한 후 영역별 신호분석 패턴을 정형화하였다. 유형별로 다소 차이를 보이나 두 영역의 이미지 분석 결과는 차별성을 보였다. 문자 영역은 grey level 범위가 좁고 한정되며 일관성을 보이는데 비해, 바탕영역은 범위가 넓고 광범위하였다. 두 영역의 교차 레벨 범위는 극히 제한적이었으며 패턴 분리에 큰 영향을 끼치지 못하였음이 밝혀졌다. 이 일련의 과정은 알고리즘화되어, 1-2분 정도의 사전 작업만 하면 프로그램에 의해 문자를 추출할 수 있다. 이러한 사실들은 종래 무리한 탁본 작업에만 전적으로 의존하던 금석학 분야의 디지털화를 가능케 할 수 있다.

• 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.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.21-26
• /
• 2004

Color image quantization is a process of selecting a set of colors to display an image with some representative colors without noticeable perceived difference. It is very important in many applications to display a true color image in a low cost color monitor or printer. The basic problem is how to display 256 colors or less colors, called color palette, In this paper, we propose improved binary tree vector quantization based on spatial sensitivity which is one of the human visual properties. We combine the weights based on the responsibility of human visual system according to changes of three Primary colors in blocks of images with the process of splitting nodes using eigenvector in binary tree vector quantization. The test results show that the proposed method generates the quantized images with fine color and performs better than the conventional method in terms of clustering the similar regions. Also the proposed method can get the better result in subjective quality test and WSNR.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.602-606
• /
• 2008

LCD is supplied light by BLU(Back Light Unit) and the light represents color by each color filter. Also LCD adjusts the amount of light by controlling liquid crystal between the glass of upper plate and one of lower. However, it is impossible to completely exclude light due to the structural and physical characteristic of liquid crystal. Therefore, on transfering light through optical sheet and liquid crystal, many problems are generated. They are related with energy efficiency and get effective for the contrast of LCD to have lower contrast ratio than other display devices. To solve the problems, many techniques have been studied and developed but don't exist keys to solution for them. Among methods, local dimming is one example to be applied to LCD. In this paper we propose image processing algorithm for local dimming of BLU of LED used as light source. The proposed algorithm extracts maximum luminance signal and lights using each extracted signal on segmented region of BLU. Also the proposed algorithm generates image signal in corresponding to luminance of the segmented region and supplies them with LCD panel to represent image with improving luminance ratio.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.3
• /
• pp.129-135
• /
• 2011

In this paper, we propose the algorithm using optical flow and machine learning-based segmentation for the 3D conversion of 2D video. For the segmentation allowing the successful 3D conversion, we design a new energy function, where color/texture features are included through machine learning method and the optical flow is also introduced in order to focus on the regions with the motion. The depth map are then calculated according to the optical flow of segmented regions, and left/right images for the 3D conversion are produced. Experiment on various video shows that the proposed method yields the reliable segmentation result and depth map for the 3D conversion of 2D video.

• 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.

• Journal of Digital Contents Society
• /
• v.1 no.1
• /
• pp.53-64
• /
• 2000

This paper is related to color image segmentation scheme which makes it possible to achieve the excellent segmented results by block-based segmentation using Y/C bit-plane summation image. First, normalized chrominance summation image is obtained by normalizing the image which is summed up the absolutes of color-differential values between R, G, B images. Secondly, upper 2 bits of the luminance image and upper 6bits of and the normalized chrominance summation image are bitwise operated by the pixel to generate the Y/C bit-plane summation image. Next, the Y/C bit-plane summation image divided into predetermined block size, is classified into monotone blocks, texture blocks and edge blocks, and then each classified block is merged to the regions including one more blocks in the individual block type, and each region is selectively allocated to unique marker according to predetermined marker allocation rules. Finally, fine segmented results are obtained by applying the watershed algorithm to each pixel in the unmarked blocks. As shown in computer simulation, the main advantage of the proposed method is that it suppresses the over-segmentation in the texture regions and reduces computational load. Furthermore, it is able to apply global parameters to various images with different pixel distribution properties because they are nonsensitive for pixel distribution. Especially, the proposed method offers reasonable segmentation results in edge areas with lower contrast owing to the regional characteristics of the color components reflected in the Y/C bit-plane summation image.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.3
• /
• pp.97-107
• /
• 1997

Image segmentation is teh important step in image infromation extraction for computer vison sytems. Fuzzy clustering methods have been used extensively in color image segmentation. Most analytic fuzzy clustering approaches are derived from the fuzzy c-means (FCM) algorithm. The FCM algorithm uses th eprobabilistic constraint that the memberships of a data point across classes sum to 1. However, the memberships resulting from the FCM do not always correspond to the intuitive concept of degree of belongingor compatibility. moreover, the FCM algorithm has considerable trouble above under noisy environments in the feature space. Recently, the possibilistic C-mean (PCM) for solving growing for color image segmentation. In the PCM, the membersip values may be interpreted as degrees of possibility of the data points belonging to the classes. So, the problems in the FCM can be solved by the PCM. The clustering results by just PCM are not smoothly bounded, and they often have holes. So, the region growing was used as a postprocessing. In our experiments, we illustrated that the proposed method is reasonable than the FCM in noisy enviironments.