• 정보처리학회논문지B
• /
• 제13B권4호
• /
• pp.409-416
• /
• 2006

본 논문에서는 스팸메일 영상에서 텍스트 영역의 추출을 위한 색상 레이어기반의 알고리즘을 제안한다. CLTE(color layer-based text extraction)는 색상 레이어를 사용하여 영상을 8개로 나눈다. 8개 각각의 영상에서 연결요소를 추출한 후, 연결요소의 크기에 의해서 텍스트 영역과 비텍스트 영역을 분류하고 텍스트 영역을 추출한다. 또한, 추출된 텍스트 영역으로부터 회손된 획 정보를 복구하는 알고리즘을 제안한다. 이진영상내의 한글 문자에는 두 가지 형태의 손상된 획이 존재한다. 첫째 중성 획에 해당하는 'ㅣ' 나 'ㅡ' 등의 획들이 지워지는 경우와, 둘째 초 종성 획에 해당하는 'ㅁ' 이나 'ㅇ'이 흑화소로 채워지는 경우가 있다. 제안한 알고리즘은 이러한 두 가지 손상된 획들을 복구해준다. 200개의 스팸메일 영상을 사용한 실험 결과 제안한 알고리즘이 기존의 텍스트 추출 알고리즘보다 10% 이상 우수함을 관측하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1281-1285
• /
• 2004

There are numerous emotions in the human world. Human expresses and recognizes their emotion using various channels. The example is an eye, nose and mouse. Particularly, in the emotion recognition from facial expression they can perform the very flexible and robust emotion recognition because of utilization of various channels. Hybrid-feature extraction algorithm is based on this human process. It uses the geometrical feature extraction and the color distributed histogram. And then, through the independently parallel learning of the neural-network, input emotion is classified. Also, for the natural classification of the emotion, advancing two-dimensional emotion space is introduced and used in this paper. Advancing twodimensional emotion space performs a flexible and smooth classification of emotion.

• 한국멀티미디어학회논문지
• /
• 제18권4호
• /
• pp.460-472
• /
• 2015

Most of previous visual attention system finds attention regions based on saliency map which is combined by multiple extracted features. The differences of these systems are in the methods of feature extraction and combination. This paper presents a new system which has an improvement in feature extraction method of color and motion, and in weight decision method of spatial and temporal features. Our system dynamically extracts one color which has the strongest response among two opponent colors, and detects the moving objects not moving pixels. As a combination method of spatial and temporal feature, the proposed system sets the weight dynamically by each features' relative activities. Comparative results show that our suggested feature extraction and integration method improved the detection rate of attention region.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
• /
• pp.521-524
• /
• 2003

In this paper, we propose a face region extraction algorithm using color information and projection. After the extraction of face candidate image using adaptive color information, we project it into vertical direction to estimate the width of the face. Then the redundant parts of the face are efficiently removed by using the estimated face width. And the width information of the face is used at the horizontal projection step to extract the height of the face, and non-face region such as the neck and some background regions, which are represented as the similar skin color, effectively eliminated. From the experiment results for the various images, the proposed algorithm shows more accurate results than the conventional algorithm.

• International Journal of Contents
• /
• 제8권4호
• /
• pp.95-102
• /
• 2012

In this paper, we present a technique to extract the title areas from book cover images. A typical book cover image may contain text, pictures, diagrams as well as complex and irregular background. In addition, the high variability of character features such as thickness, font, position, background and tilt of the text also makes the text extraction task more complicated. Therefore, we propose a two steps efficient method that uses Histogram of Oriented Gradients and color information to find the title areas. Firstly, text localization is carried out to find the title candidates. Finally, refinement process is performed to find the sufficient components of title areas. To obtain the best result, we also use other constraints about the size, ratio between the length and width of the title. We achieve encouraging results of extracted title regions from book cover images which prove the advantages and efficiency of the proposed method.

• 한국염색가공학회지
• /
• 제12권4호
• /
• pp.239-247
• /
• 2000

The coloring matter was extracted from the heartwood of Amur cork tree by distilled water. Change of UV-Visible spectra of coloring matter solution by extraction condition and stability for irradiation were determined, and the effect of repeated dyeing with condition of dyebath and mordanting method on shade depth and lightfastness were also investigated. The results are as follows : 1) Absorbance of Amur cork tree extract increased with the lapse of extraction time. λmax of color solution extracted from Amur cork tree was found at 420, 333, and 262nm. 2) Absorbance of Amur cork tree extract decreased remarkably after 2hr irradiation. 3) The K/S of silk fabrics increased with the increase of dyeing temperature, time, amounts of Amur cork tree for extraction, and pH of color solution. 4) K/S of silk fabrics dyed by repeated dyeing method was affected by pH and concentration of color solution. 5) Lightfastness of silk twice dyed with Amur cork tree extract after pre-mordanted by 8%(o.w.f) chromium acetate was moderately improved.

• 한국식품영양학회지
• /
• 제11권4호
• /
• pp.375-380
• /
• 1998

A study of characteristics of greenish pigments from silkwarm excrement by ethanol extraction. Through visible absorption scanning, it showed two absorption peaks at 415 and 657nm, and it was shown to be greenish color. In the presence of light, the stability of pigments rapidly degraded, but in the presence of Al-foil, green and blue cover were very stable. It was shown to be stabilized at the temperature of 7$0^{\circ}C$ until 20days and presence of metal ions, such as Na+, K+, Ca2+, Mg2+ and Zn2+. The pigments was shown to be stabilized in 5% acetic acid solution, but in the presence of lactic acid, citric acid and tartaric acid solution were unstable. On the result of TLC analysis, pigments were shown to be composed of eight color fractions, and main color fractions were F-1, F-2 and F-3. In F-1, F-2 fractions were revealed green color and F-3 fraction were revealed yellow color.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.222-224
• /
• 2009

This paper presents an algorithm that extracts road lane's specific information by using HSI color information and performance enhancement of lane detection base on vision processing of drive assist. As a preprocessing for high speed lane detection, the optimal extraction of region of interest for lane boundary(ROI-LB) can be processed to reduction of detection region in which high speed processing is enabled and it also increases reliabilities by deleting edges those are misrecognized. Road lane is extracted with simultaneous processing of noise reduction and edge enhancement using the Laplacian filter, the reliability of feature extraction can be increased for various road lane patterns. Since noise can be removed by using saturation and brightness of HSI color model. Also it searches for the road lane's color information and extracts characteristics. The real road experimental results are presented to evaluate the effectiveness of the proposed method.

• 복식문화연구
• /
• 제19권3호
• /
• pp.612-621
• /
• 2011

The process of making or cultivating indigo dyes is very cumbersome and complex. The dye extraction and dyeing methods using general plant dye, moth repellent dye, fast acting natural dye, and other dyes are very different. This research investigates the extraction of indigo dye and liquid dye extraction of polygonum(indigo) plants using calcium oxide water. While extracting indigo dye the concentration of purified indigo dye may be controlled by adjusting the pH level. Due to the various uses of dyes the adjustment of surface color must be considered. In regard to the change according to different concentrations of reducing agents, it was found that cotton fabrics and ramie fabrics show the highest color difference at 0.4% and 0.3% respectively. As the reduction temperature increases, the color difference increases as well. The maximum color difference was found to appear at $90^{\circ}C$. Cotton fabrics and ramie fabrics showed 70.55 and 67.01 respectively. The color difference increases as the concentration of dyes increases, but at a concentration of 300%, cotton fabrics was found to show 6.22PB in H value using the Munsell color system, containing purple and blue color. The pH of the polygonum dyes extracted through this experiment were adjusted by adding calcium oxide to the experimental water, without directly adding calcium oxide to the liquid polygonum extract. In a refine state, it was mixed with polygonum extract to extract a more refine and highly concentrated indigo dye. When lye and reducing agents are added to extracted indigo dye and sealed for long-term storage, it can be effective and easily used for dyeing.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1835-1838
• /
• 2003

이미지에 포함되어 있는 텍스트들은 이미지의 내용을 함축적이며 구체적으로 표현하는 정보를 갖고 있다. 본 논문에서는 이러한 정보를 정확히 추출하기 위해서 색 변화 특징을 이용한 텍스트 영역 추출 방법을 제안한다. 관찰에 의하면 이미지 내의 텍스트들은 주변 배경과의 색 변화가 존재하며, 이러한 색 변화를 3차원 RGB공간에서 표현한다면, 명도이미지에서의 밝기 변화에서 표현하기 어려운 영역들을 강조시킬 수 있으며, 조명 변화에도 민감하지 않은 결과를 만들어 낼 수 있다. 색 변화 정도는 3차원 RBG 공간에서의 색 분산(Variance)으로 측정한다 처리 과정으로서 우선 수평 및 수직 방향의 분산 이미지를 구하는데, 텍스트 영역은 두 방향의 분산 값이 모두 높은 특징이 있다. 다음으로 두 결과의 논리적 AND 연산을 수행하여 불필요한 잡영들을 제거한 후 연결요소를 분석, 검증하여 영역을 최종 확정한다. 다양한 종류의 자연이미지로 제안한 방법을 검증한 결과 밝기 변화 또는 색 연속성 특징들을 이용한 방법에서 찾기 어려운 텍스트 영역들을 찾을 수 있는 것을 확인할 수 있었다.