• 정보처리학회논문지B
• /
• 제11B권4호
• /
• pp.403-410
• /
• 2004

최근 의료 영상 분석(Medical Image Analysis)이나 영상 검색(Image Retrieval)을 위한 전처리(Preprocessing) 단계로 영상 분석(Image Analysis)에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 영상 검색에서 색상 성분(Color Component)의 활용 방법을 제안하고자 한다. 이미지를 검색하기 위해 색상 성분을 기반으로 하고, 색상(Color)을 분석하기 위한 기법으로 CLCM(Color Level Co-occurrence Matrix)과 통계적 기법을 이용하고 있다. CLCM은 기하학적 회전 변환(Geometric Rotate Transform)을 통해서 색상 성분을 3차원 공간상에 투영(Projection)하여 공간 관계(Spatial Relationship)로부터 나타나는 분포를 해석하는 방법으로, 본 논문에서 제안하는 주제이다. CLCM은 색상 모델에서 만들어지는 2차원 히스토그램을 지칭하며 색상 모델의 기하학적인 회전 변환을 통해서 생성된다. 그리고 이를 분석하기 위한 방법으로 통계 기법을 활용하고 있다. CLCM과 유사하게 2차원 분포도를 사용하는 GLCM(Gray Level Co-occurrence Matrix)[1]과 불변 모멘트(Invariant Moment)[2,3] 같은 알고리즘은 2차원적인 데이터를 해석하기 위하여 기본적인 통계 기법을 활용하고 있다. 하지만 GLCM과 불변 모멘트가 각각의 도메인에 최적화되어 있다 하더라도 공간 좌표상에 존재하는 불규칙적인 데이터를 완전히 해석할 수는 없다. 즉 GLCM과 불변 모멘트는 기초 통계 기법만을 사용하고 있기 때문에 추출된 특징들의 신뢰성이 낮다는 것이다. 본 논문에서는 이러한 단점을 보완하여 공간 관계를 해석함과 동시에 데이터의 가중치를 해석하기 위해 전형적인 다변량 통계에서 사용하는 주성분 분석(Principal Component Analysis)[4,5]을 이용하고 있다. 그리고 데이터의 정확도를 높이기 위해서 3차원 공간상에 색상 성분을 투영하여 이를 회전시키면서 데이터의 특성을 다각도에서 추출하는 방법을 제시한다.

• 스마트미디어저널
• /
• 제1권4호
• /
• pp.27-34
• /
• 2012

In this paper, a novel text binarization is presented that can deal with some complex conditions, such as shadows, non-uniform illumination due to highlight or object projection, and messy backgrounds. To locate the target text region, a focus line is assumed to pass through a text region. Next, connected component analysis and stroke width estimation based on location information of the focus line is used to locate the bounding box of the text region, and each box of connected components. A series of classifications are applied to identify whether each CC(Connected component) is text or non-text. Also, a modified K-means clustering method based on an HCL color space is applied to reduce the color dimension. A text binarization procedure based on location of text component and seed color pixel is then used to generate the final result.

• Journal of Periodontal and Implant Science
• /
• 제31권3호
• /
• pp.501-511
• /
• 2001

Several indices have been developed that use bleeding and color changes as indicators of early gingival pathology. In the presence of gingivitis, vascular proliferation and reduction of keratinization owing to increase redness in gingiva. Descriptions of healthy gingiva are numerous, ranging from pale pink and coral pink to deep red and violet. This terms are not objective. Because of perception of color depends on a lot of factors such as light source, object, observer and so on. It is difficult to make an objective expression. Therefore the using of mechanical equipment is recommended to exclude these variables and observer's vias. The purpose of this study was to evaluate gingival color change after scaling & subgingival root planing. The other purpose of this study was to research the correlation of pocket depth, P.B.I. score and gingival color change. After photo-taking and storaging the image of gingival color into a computer, color change was examine with an image analysis program. Results were as follow; 1. Color of healed gingiva after scaling & subgingival root planing was significantly differ from color of inflamed gingiva(p<0.01). 2. Color of healed gingiva after scaling was similar to color of healed gingiva after subgingival root planing(p<0.05). 3. There was statistically significant correlation between color change of red component and pocket depth after scaling & subgingival root planing(p<0.01). 4. There was no correlation between color change of green, blue component and pocket depth after scaling & subgingival root planing(p<0.01). 5. There was statistically significant correlation between between color change of red component and P.B.I. score after scaling & subgingival root planing(p<0.01). 6. There was no correlation between color changes of green, blue component and P.B.I. score after scaling & subgingival root planing(p<0.01). 7. Increase of pocket depth and P.B.I. score were significantly correlated to the amount of color change(p<0.01). 8. P.B.I. score had a higher correlation with color change than pocket depth(p<0.01).

• 한국컴퓨터정보학회논문지
• /
• 제12권3호
• /
• pp.131-136
• /
• 2007

본 논문에서는 컬러영상에 존재하는 문자들을 효율적으로 추출하기 위한 새로운 접근 방법을 제안한다. 빛 또는 조명성분의 영향에 의해 획득된 영상 내에 존재하는 반사성분은 문자 또는 관심객체들의 경계가 모호해 지거나 관심객체와 배경이 서로 혼합 되었을 경우, 문자추출 및 인식을 함에 있어서 오류를 포함시킬 수 있다. 따라서 영상 내에 존재하는 반사성분을 제거하기 위해 먼저. 컬러영상으로부터 Red컬러 성분에 해당하는 히스토그램에서 두개의 pick점을 검출한다. 이후 검출된 두 개의 pick점들 간의 분포를 사용하여 노말 또는 편광 영상에 해당하는지를 판별한다. 노말 영상의 경우 부가적인 처리를 거치지 않고 문자에 해당하는 영역을 검출하며, 편광 영상에 해당하는 경우 반사성분을 제거하기 위해 호모모픽필터링 방법을 적용하여 반사성분에 해당하는 영역을 제거한다. 이후 문자영역을 검출하기 위해 최적전역임계화방식을 적용하여 전경과 배경을 분리하였으며 문자영역 추출 및 인식의 성능을 향상시켰다. 널리 사용되고 있는 문자 인식기를 사용하여 제안한 방식 적용 전과 후의 인식결과를 비교하였다. 편광영상에서 제안된 방법 적용 후, 문자인식을 한 경우 인식률이 향상되었다.

• 정보처리학회논문지B
• /
• 제15B권3호
• /
• pp.229-236
• /
• 2008

본 논문은 화자의 입술 움직임으로부터 음성을 인식하는 자동 독순에서 회색조 영상 대신 컬러 영상을 사용하는 것의 유용성에 대해 고찰한다. 먼저 인간의 독순 실험을 통해 컬러 정보가 인식 성능에 어떠한 영향을 미치는지 확인한다. 다음으로 주성분분석을 이용한 자동 독순에서 회색조 또는 컬러 입술영상을 사용하는 경우에 대해 인식 성능을 비교한다. 다양한 컬러 좌표계에 대한 실험을 통해 컬러 영상의 사용으로 인식율이 향상됨을 보인다. 특히 RGB 좌표계를 사용했을 때 가장 좋은 성능을 얻으며, 회색조의 경우에 비해 잡음이 없는 환경에서는 4.7%, 잡음이 있는 경우 평균 13.0%의 상대적 오인식율 감소를 얻을 수 있음을 확인한다.

• 센서학회지
• /
• 제29권2호
• /
• pp.133-140
• /
• 2020

This study proposes a method of blending visible and near infrared images to enhance edge details and local contrast. The proposed method consists of radiance map generation and color compensation. The radiance map is produced by a Laplacian pyramid and a soft mixing method based on principal component analysis. The color compensation method uses the ratio between the composed radiance map and the luminance channel of a visible image to preserve the visible image chrominance. The proposed method has better edge details compared to a conventional visible and NIR image blending method.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 2000년도 제31회 춘계학술대회
• /
• pp.54-61
• /
• 2000

A method and results of classification of 4 types metallic wear debris were presented by using their color features. The color image of wear debris was used (or the initial data, and the color properties of the debris were specified by HSI color model. Particle was characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used for the definition of classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• 한국응용과학기술학회지
• /
• 제28권4호
• /
• pp.393-401
• /
• 2011

Natural Curcumin belongs to Zingiber Officinale Roscoe was known to possess natural odor, natural taste, natural color, and other pharmaceutical & chemical characteristics. Natural Curcumin extract was made to use ethanol as a solvent was to show a yellow color having state of solid powder and an active component. Natural Curcumin extract tested pharmaceutical & chemical experiment to dilute in curcumin 1%-water solution. Curcumin extract tested antimicrobial experiment using microbe, and tested dye experiment using fiber. Some conclusions in the result of characteristics experiment was obtained as follow. The result of antimicrobial experiment showed that the growth of staphylococcus aureus (ATCC-001) and aspergillus niger (ATCC-002) as microbes decreased according to passage of time. This phenomenon could know that Curcumin compoment showed influence to antimicrobial effect. Also, the result of dye experiment showed that cotton and sick with fiber dyeing dyed in direction of dark yellow color. This phenomenon could know that Curcumin extract showed influence to dyeing effect in observation of optical electron microscope(OEM.) The result of instrument analysis ascertained inorganic components of K(53.300ppm), Na(1.150ppm), Ca(0.711ppm), Ti(0.351ppm), Li(0.256ppm), Cu(0.233ppm) etcs from Curcumin component with ICP/OES, and ascertained organic components of propanoic acid(1.859), benzene(10.814), phenol(14.194) etcs from Curcumin component with GC/MSD.

• Journal of the Korean Data and Information Science Society
• /
• 제15권4호
• /
• pp.817-823
• /
• 2004

This paper describes a three dimensional motion recognition algorithm and a system which adopts the algorithm for non-contact human-computer interaction. From sequence of stereos images, five feature regions are extracted with simple color segmentation algorithm and then those are used for three dimensional locus calculation precess. However, the result is not so stable, noisy, that we introduce principal component analysis method to get more robust motion recognition results. This method can overcome the weakness of conventional algorithms since it directly uses three dimensional information motion recognition.

• Current Optics and Photonics
• /
• 제6권6호
• /
• pp.608-618
• /
• 2022

By analyzing the signal-to-noise ratio (SNR) theory of the conventional true color night vision system, we found that the output image SNR is limited by the wavelength range of the system response λ₁ and λ₂. Therefore, we built a double-channel four-band true color night vision system to expand the system response to improve the output image SNR. In the meantime, we proposed an image fusion method based on principal component analysis (PCA) and nonsubsampled shearlet transform (NSST) to obtain the true color night vision images. Through experiments, a method based on edge extraction of the targets and spatial dimension decorrelation was proposed to calculate the SNR of the obtained images and we calculated the correlation coefficient (CC) between the edge graphs of obtained and reference images. The results showed that the SNR of the images of four scenes obtained by our system were 125.0%, 145.8%, 86.0% and 51.8% higher, respectively, than that of the conventional tri-band system and CC was also higher, which demonstrated that our system can get true color images with better quality.