A study of a method for distribution analysis of skin color

Ha, Seunghan,Lee, Minhee,Lee, Onseok,Lee, Gunwoo,Kim, Jeayoung,Moon, Jongsub,Kim, Mingi,Oh, Chilhwan Blackwell Publishing Ltd 2009 SKIN RESEARCH AND TECHNOLOGY Vol.15 No.2

<P>Background/aims</P><P>The objective and quantitative assessment of the skin is important in medical and cosmeceutical research. Assessment of color is an important element for analyzing the surface of the skin, which is usually determined subjectively by a doctor or using color analysis devices. These devices, however, cannot provide correct color information because color is construed from the mean value of the observation region, and analysis of color distribution is impossible. The purpose of this paper is to develop an objective analysis method to permit skin color measurement of each pixel unit of an image and analyze the distribution of skin surface color.</P><P>Methods</P><P>The Skin Color Distribution Analyzer (SCDA) is an analysis method newly developed at the Research Institute for Skin Image at Korea University. The SCDA system presented in this paper performed a novel form of quantitative and objective analysis of skin color distribution using each pixel color model parameter found in image wavelength information.</P><P>In this paper, distribution analysis was conducted on normal skin and skin lesions and skin affected by artificially induced irritant contact dermatitis and pigmented nevous. The method selected a grade using a color model parameter. Twenty healthy Korean males participated in this study. A comparative study of the eight anatomical areas was performed, including the exposure and non-exposure parts and the medial aspect and the lateral aspect of the forearm. A reliability test for the SCDA system was also conducted with a spectrometer (SPEC) using the color analysis method.</P><P>Results</P><P>Each skin lesion was precisely segmented by grade and each parameter hada different statistical significance for results of analysis of distribution in pigmented nevous and the artificially induced irritant contact dermatitis. Parameters <I>L</I><SUP>*</SUP>, <I>b</I><SUP>*</SUP>, <I>a</I><SUP>*</SUP>, and EI showed salient traits. Showed resemble measured result in the SCDA system and the SPEC of normal skin. The exposed site, in comparison with the non-exposed site, showed a notable difference in the <I>L</I><SUP>*</SUP> parameter and a significant statistical difference in the <I>x</I> and <I>z</I> parameters, except <I>b</I><SUP>*</SUP>. The comparison of the medial and lateral aspects of the forearm showed a notable difference in the <I>L</I><SUP>*</SUP> parameter and a significant statistical difference in the parameters except <I>y</I> and <I>b</I><SUP>*</SUP>. In the reliability test result using the SCDA system and the SPEC, the SCDA system was highly reliabile in terms of the CV value in all color model parameters.</P><P>Conclusions</P><P>The color distribution analysis method using the SCDA system has revealed an aspect that the existent method of medical research has not shown, and is considered to be more reliable than other methods. This method can provide better study findings because it can be applied to other fields in addition to the medical science field and the ripple effect is thought to be bigger in other science field too.</P>

머신러닝과 KSCA를 활용한 디지털 사진의 색 분석 -한국 자연 풍경 낮과 밤 사진을 중심으로-

권희은,구자준 성균관대학교 트랜스미디어연구소 2022 트랜스- Vol.12 No.-

This study investigates the methods for deriving colors which can serve as a reference to users such as designers and or contents creators who search for online images from the web portal sites using specific words for color planning and more. Two experiments were conducted in order to accomplish this. Digital scenery photoswithin the geographic scope of Korea were downloaded from web portal sites, and those photos were studied to find out what colors were used to describe daytime and nighttime. Machine learning was used as the study methodology to classify colors in daytime and nighttime, and KSCA was used to derive the color frequency ofdaytime and nighttime photos and to compare and analyze the two results. The results of classifying the colors of daytime and nighttime photos using machine learning show that, when classifying the colors by 51~100%, the area of daytime colors was approximately 2.45 times greater than that of nighttime colors. The colors of the daytime class were distributed by brightness with white as its center, while that of the nighttime class was distributed with black as its center. Colors that accounted for over 70% of the daytime class were 647, those over 70% of the nighttime class were 252, and the rest (31-69%) were 101. The number of colors in the middle area was low, while other colors were classified relatively clearly into day and night. The resulting color distributions in the daytime and nighttime classes were able to provide the borderline color values of the two classes that are classified by brightness. As a result of analyzing the frequency of digital photos using KSCA, colors around yellow were expressed in generally bright daytime photos, while colors around blue value were expressed in dark night photos. For frequency of daytime photos, colors on the upper 40% had low chroma, almost being achromatic. Also, colors that are close to white and black showed the highest frequency, indicating a large difference in brightness. Meanwhile, for colors with frequency from top 5 to 10, yellow green was expressed darkly, and navy blue was expressed brightly, partially composing a complex harmony. When examining the color band, various colors, brightness, and chroma including light blue, achromatic colors, and warm colors were shown, failing to compose a generally harmonious arrangement of colors. For the frequency of nighttime photos, colors in approximately the upper 50% are dark colors with a brightness value of 2 (Munsell signal). In comparison, the brightness of middle frequency (50-80%) is relatively higher (brightness values of 3-4), and the brightness difference of various colors was large in the lower 20%. Colors that are not cool colors could be found intermittently in the lower 8% of frequency. When examining the color band, there was a general harmonious arrangement of colors centered on navy blue. As the results of conducting the experiment using two methods in this study, machine learning could classify colors into two or more classes, and could evaluate how close an image was with certain colors to a certain class. This method cannot be used if an image cannot be classified into a certain class. The result of such color distribution would serve as a reference when determining how close a certain color is to one of the two classes when the color is used as a dominant color in the base or background color of a certain design. Also, when dividing the analyzed images into several classes, even colors that have not beenused in the analyzed image can be determined to find out how close they are to a certain class according to the color distribution properties of each class. Nevertheless, the results cannot be used to find out whether a specific color was used in the class and by how much it was used. To investigate such an issue, frequency analysis was conducted using KSCA. The color frequency could be measured within the range of images used in the experiment. The resulting valu...

미디어 파사드 사례의 색채 연구

김주연(Kim, Ju Yeon) 한국디지털디자인협의회 2013 디지털디자인학연구 Vol.13 No.2

본 연구는 국내 및 해외의 미디어 파사드가 나아가야할 방향을 제시하고자 색채 분석을 중심으로 특성을 살펴보았다. 연구 방법 및 단계로는 첫째, 국내와 국외로는 뉴욕, 싱가포르와 베이징을 방문하여 직접 선정된 12곳의 연구 사례들을 조사하고 특징과 색채를 측정하였다. 각 사례는 직접 육안을 통해 디지털 미디어의 변화에따라 디지털 카메라 촬영과 색채 휘도계 CS-100s 기기로 색차이, 색도, 휘도를 측정하였다. 둘째, 연구 분석 단계는 물리적인 기계 측정 분석과 인지 평가를 위한 설문으로 나뉘어 진행되었다. 색공간 분포도의 측정된 데이터는 시간에 따른 색차이 및 색도에 대한 값으로 CIE 색 좌표에 의해 색채를 추출하여 개발된 CIE 컬러 애널라이저(CIE Color Analyzer) 프로그램에 의해 분석 하였다. 미디어 파사드의 색채 인지를 평가하기 위하여 건축, 디자인 전공 교육을 받은 대학생 40명과 대학원생 20명으로 동일한 남자 여자 비율로 총 60명의 피험자에게 연구 사례의 영상을 자극물로 제시하였다. 설문을 통하여 실제 보행자나 일반인이 느끼는 미디어 파사드 색선호도와 대표 색인지를 통계적 검증을 통해 평가할 수 있었다. 연구 결과 미디어 파사드의 재료에 따라 동일 색채에서도 색 차이를 볼 수 있었으며, 연구사례들의 색채 분포 값을 볼 수 있었다. 본 연구는 미디어 파사드의 색채 구성이 도시 미관의 기능을 넘어 건축적 재료로써 역할 수행의 중요성을 강조하며 색채 특성 평가 방법과 구성 방식의 방법을 제안하기 위한 색채 데이터베이스 구축을 최종 목적으로 하였다. 향후 본 연구의 색채 데이타는 그 자체만으로도 미디어 파사드 디자인을 위한 색채 제안에 중요한 영향을 줄 수 있을 것이다. This study to suggest better to go the direction of domestic and foreign media facade color analysis characteristics were investigated. First, the domestic and international research methods and step into the New York, Singapore and Beijing to visit the direct selection of 12 case studies to investigate the characteristics and color were measured. Direct vision through each case in accordance with changes in the digital media devices with digital camera shooting, and the color luminance meter CS-100s, chromaticity, color difference, luminance was measured. Color space distribution of the measured data were analyzed by the program on the development by the colors in the CIE chromaticity coordinates to extract the value of the color difference and color according to the time on the CIE color analyzer. Architecture, design majors trained college students in order to evaluate the color of the media facade is name and the same men and women, graduate students to 20 people at a rate 40 to a total of 60 subjects as a case study of video irritant presented. Actual pedestrian survey or feel the public media facade color preference and how representative index through statistical verification could be evaluated. As a results, depending on the material of the media facade could see the difference in color in the same color, you could see the color distribution of values. Architectural feature of the cityscape beyond the color configuration of the media facade materials emphasize the importance of performing the role as the final color to build a database, and propose a method of evaluation methods and configuration methods chromatic characteristics for this study purpose. The color data of the future, this study itself will be able to give a significant impact on the media facade design suggestions for colors.

Object Motion Tracking using a Moving Direction Estimate and Color Updates

Samuel Henry Chang,심덕선,김희영,최광남 제어·로봇·시스템학회 2012 International Journal of Control, Automation, and Vol.10 No.1

This paper presents a direction detection and tracking object color update algorithm used to track moving objects that change colors. Different from traditional color-based tracking methods, which use an initial color distribution in order to track objects as long as the object carries the full or partial initial color, this method introduces a color update method used to quickly find the new object color in a new location if the object changes its color partially or completely; the updated color is then used to locate the object. In our algorithm, an initial color pattern is used to track an object using the color. During the tracking, an object’s new location is at first estimated and then used to detect any color change. If the color has changed, a new color pattern is updated based on the changes in the previous color distribution, and then the new color pattern is used to calculate the current location of the object. This algorithm utilizes the property that the movement of an object can be estimated either by using the object’s shadow or by background subtraction. The implementation of our algorithm results in an effective real-time object tracking. The validity of the approach is illustrated by the presentation of experiment results obtained using the methods described in this paper.

색채자극 전과 후 달라진 색 사용에 관한 연구

김선화 ( Sun Hwa Kim ),이승희 ( Seung Hee Lee ) 한국감성과학회 2009 감성과학 Vol.12 No.3

본 연구에서는 피험자의 경험에 의한 학습의 정도가 색사용에 어떠한 영향을 주고 있으며 그 요소는 무엇인지를 찾아보는 것에 있다. 본 실험에서는 서로 다른 두 유명작품을 자극으로서 사용하였으며, 피험자에게 자극의 전과 후, 같은 패턴에 색칠하기를 그려 받았다. 자극의 전후에 그려 받은 색칠하기에서 선택한 색과 색 양, 색 수, 색의 구성의 변화를 비교 분석함으로써 자극으로부터 받은 요인을 찾아보고자 한다. 본 연구는 경험의 정도가 다른 어른과 어린이의 색사용의 변화를 비교한 선행실험의 결과를 토대로 하였다. 본 실험에서는 전공에 의한 학습경험의 정도가 다른 디자인 전공자와 비 디자인전공자의 색사용의 변화를 비교해 보였다. 결과로부터 디자인 전공자의 경우, 색의 자극이 다양했던 모네그림의 자극 후에는 색 수의 감소 현상이 나타났으며 자극의 그림에서 사용된 색의 선택이 높아지거나 색 양이 증가하는 경향이 보였다. 비 디자인전공자의 경우, 몬드리안그림의 자극 후 자극전의 색 수보다 감소하는 반대의 경향이 나타났으며, 다자인선공자와 비교하였을 때 선택한 색과 색 양의 변화는 있었지만 불규칙적인 경향을 나타내었다. The study is about how the difference in education levels can affect the subjects` use of color and find out the features of the effect. This experimental study focused on the differences in color expression using the outline picture of a painting before and after being exposed to a full-color picture of the original painting. Differences between two conditions with two different stimuli were observed and the cause of the differences was analyzed based on the number of colors and the quantity of colors and composition of the colors used by the subjects. The study precedes an experiment based on how the level of education though experience can affect the use of colors. This study is focused on the various effects of color usage by children and adults who have various degrees of visual experience. In addition, the study analyzes how design majored subject differed in the use of color from non-design majored subject and compares the use of colors by the two groups. The results showed that design majored subject tended to use less coloring patterns after seeing the stimulus of the Monet picture with more colors, and included the colors from the stimuli they were exposed to. The non-design majored subject who viewed the Mondrian painting demonstrated opposite results by using less number of colors than before seeing the stimuli. In comparison to design majored subject, the variations in selected colors and the quantity of color by non-design majored subject were not consistent.

Saliency Detection based on Global Color Distribution and Active Contour Analysis

( Zhengping Hu ),( Zhenbin Zhang ),( Zhe Sun ),( Shuhuan Zhao ) 한국인터넷정보학회 2016 KSII Transactions on Internet and Information Syst Vol.10 No.12

In computer vision, salient object is important to extract the useful information of foreground. With active contour analysis acting as the core in this paper, we propose a bottom-up saliency detection algorithm combining with the Bayesian model and the global color distribution. Under the supports of active contour model, a more accurate foreground can be obtained as a foundation for the Bayesian model and the global color distribution. Furthermore, we establish a contour-based selection mechanism to optimize the global-color distribution, which is an effective revising approach for the Bayesian model as well. To obtain an excellent object contour, we firstly intensify the object region in the source gray-scale image by a seed-based method. The final saliency map can be detected after weighting the color distribution to the Bayesian saliency map, after both of the two components are available. The contribution of this paper is that, comparing the Harris-based convex hull algorithm, the active contour can extract a more accurate and non-convex foreground. Moreover, the global color distribution can solve the saliency-scattered drawback of Bayesian model, by the mutual complementation. According to the detected results, the final saliency maps generated with considering the global color distribution and active contour are much-improved.

Saliency Detection based on Global Color Distribution and Active Contour Analysis

Hu, Zhengping,Zhang, Zhenbin,Sun, Zhe,Zhao, Shuhuan Korean Society for Internet Information 2016 KSII Transactions on Internet and Information Syst Vol.10 No.12

In computer vision, salient object is important to extract the useful information of foreground. With active contour analysis acting as the core in this paper, we propose a bottom-up saliency detection algorithm combining with the Bayesian model and the global color distribution. Under the supports of active contour model, a more accurate foreground can be obtained as a foundation for the Bayesian model and the global color distribution. Furthermore, we establish a contour-based selection mechanism to optimize the global-color distribution, which is an effective revising approach for the Bayesian model as well. To obtain an excellent object contour, we firstly intensify the object region in the source gray-scale image by a seed-based method. The final saliency map can be detected after weighting the color distribution to the Bayesian saliency map, after both of the two components are available. The contribution of this paper is that, comparing the Harris-based convex hull algorithm, the active contour can extract a more accurate and non-convex foreground. Moreover, the global color distribution can solve the saliency-scattered drawback of Bayesian model, by the mutual complementation. According to the detected results, the final saliency maps generated with considering the global color distribution and active contour are much-improved.

색을 연상하는 경험적 요인에 따른 감성 평가법에 관한 연구(1)-도시와 자연의 연상색채 차이를 중심으로-

김선화 ( Kim Sunhwa ) 한국기초조형학회 2016 기초조형학연구 Vol.17 No.4

본 연구에서는 같은 의미의 ‘단어 또는 이미지’가 자극으로 주어진 후, 연상되는 색상에 차이가 있는지 알아보고자 하였다. 또한 피험자가 자라난 주변 환경의 요소가 연상되는 색상에 영향을 주는지도 살펴보았다. 본 연구에는 자극이 (1) ‘단어’ 즉 ‘제시어’로 주어졌을 때와 ‘이미지’ 주어진 후,연상 색상이 무엇인지와 ‘단어’와 ‘이미지’와의 차이. (2)‘환경적 경험’의 비교를 위해 피험자가 자란 환경을 ‘시골’과 ‘도시’로 구분하고 자극 후의 연상색상과 ‘시골’과 ‘도시’와의 차이. (3)‘학습적 경험’의 비교를 위해 자극 후 ‘전공그룹별’에 따른 연상 색상과 그룹별 차이. 또한 자극이 주어지는 짧은 시간도 학습적 역할을 하는가 알아보기 위해 자극 전후를 비교하였다. 그리고 가장 인상 깊었던 이미지를 선택한 후 사용색의 변화를 살펴보았다. 색사용의 차이의 비교 기준은 색상의 수(數)의 변화, 채색된 면적의 변화, 자극 전후 선택한 색 종류의 변화를 중심으로 비교하였다. 본 논문에서는 무채색 자극 결과를 중심으로 정리하였다. ‘제시어’ 자극은 ‘자연’과 ‘도시’이며, 무채색 이미지자극으로서 ‘자연이미지’와 ‘도시이미지’를 제시하여 자극 전 후의 색사용과 연상 색상의 차이를 알아보았다. 색 수의 결과, ‘자연이미지’는 사용한 색의 수가 자극 후 증가하였고, ‘도시이미지’는 반대로 감소하였다. 채색의 면적(색량)과 선택한 색에서는 ‘자연’의 제시어가 주어졌을 때 보다 무채색이미지의 자극 후가 보다 다양한 색을 사용하는 경향이 보였다. 반면, ‘도시’의 제시어가 주어졌을 때 보다 무채색이미지 자극 후가 특정색(검정, 회색, 노랑색)을 중심으로 색 사용이 증가하였다. ‘자연’ 또는 ‘도시’와 함께 연상 색상으로서 녹색(자연:75%)과 회색(도시:75%)을 떠올리는 피험자들이 비교적 많았다. ‘무채색이미지’ 자극 후 채색에 가장 영향을 받은 이미지를 선택받은 결과에서는, ‘자연전경(13번)’과 ‘야경(6번)과 빌딩숲(10번)’ 이미지가 선택되었다. 또한 ‘자연’ 제시어에서 연상되어 사용한 색상(녹색계열, 청색계열, 황색계열), ‘도시’ 제시어에서 연상되어 사용한 색상 (청색계열과 무채색)과 함께 무채색이미지 자극 후에는 무채색계열을 중심으로 색사용이 증가하였다. 특히, 도시이미지에서 두드러졌다. 이는 자극이 제시된 짧은 시간(학습적 경험)으로도 색사용에 영향을 주었다고 보여 진다. The current study aims to understand the difference in color associations when the words or image with the same semantic contents are given as stimulants. Another focus of study is to investigate whether the environment in which the subjects of the study grew up affect the colors associated. The current study looks at three factors that may influence the color association in subjects: (1) the form of stimulation, as words and images, (2) experiential experience of the subjects, in urban and rural environments, and (3) learning experience of the subjects, which includes major of study, as well as the short period of stimulation itself given during the study. In experimenting for the last factor, the subjects are asked to select the color that left the most impression, in order to observe the changes in their use of color. The criteria of color comparison was made with the changes in the number of colors used, the area in which the colors were applied, and the kinds of colors used before and after the stimulation. The current study used the conclusion focused on the results of achromatic color stimulation. Stimulant words had themes of rural and urban environments, and achromatic image stimulants had urban and rural visuals to understand the change in the subjects use of color and color association. After the experiment, it was found that subjects exposed to rural images used more colors after the stimulation, while those exposed to urban images used less colors. Rural stimulant words were observed to cause the subjects to use a higher variety of colors than achromatic rural stimulant images. In contrast, achromatic urban stimulant images caused higher uses of certain colors (black, gray, and yellow). The subjects tended to associate green with rural environment (75%) and gray with urban environment (75%). Achromatic images of "natural scenery" (No.13), "night view" (No.6), and "concrete jungle"`` (No.10) had the highest selection in terms of influence in coloring. In addition, the use of achromatic colors, along with colors associated with rural stimulant words (green, blue, yellow) and urban stimulant words (blue and achromatic colors) increased after achromatic image stimulation, especially with urban images. In this we can conclude that the short amount of time (learning experience) in which the stimulation was provided influence the color use.

Efficient Object-based Image Retrieval Method using Color Features from Salient Regions

Jaehyun An,Sang Hwa Lee,Nam Ik Cho 대한전자공학회 2017 IEIE Transactions on Smart Processing & Computing Vol.6 No.4

This paper presents an efficient object-based color image–retrieval algorithm that is suitable for the classification and retrieval of images from small to mid-scale datasets, such as images in PCs, tablets, phones, and cameras. The proposed method first finds salient regions by using regional feature vectors, and also finds several dominant colors in each region. Then, each salient region is partitioned into small sub-blocks, which are assigned 1 or 0 with respect to the number of pixels corresponding to a dominant color in the sub-block. This gives a binary map for the dominant color, and this process is repeated for the predefined number of dominant colors. Finally, we have several binary maps, each of which corresponds to a dominant color in a salient region. Hence, the binary maps represent the spatial distribution of the dominant colors in the salient region, and the union (OR operation) of the maps can describe the approximate shapes of salient objects. Also proposed in this paper is a matching method that uses these binary maps and which needs very few computations, because most operations are binary. Experiments on widely used color image databases show that the proposed method performs better than state-of-the-art and previous color-based methods.

풋고추 선별을 위한 유통 품질 인자 분석 연구

이현동 ( Hyun Dong Lee ),김우일 ( Woo Il Kim ),박회만 ( Hoe Man Park ),이예슬 ( Ye Seul Lee ) 한국농업기계학회 2023 농업기계공학 Vol.3 No.1

This study was conducted to investigate quality grading factor and consumer acceptance factor of green pepper for the marketing distribution. On the optical color difference, Hunter L, b value of green pepper was decreased at dark color and big size sample. The correlation between Hunter color value and chemical color index was r ≥ 0.8, respectively. On the texture properties, the cutting strength was increased with sample size. the cutting strength small size sample was more uniform than bigger size. According to cultivar, the distribution of capsaicin content is from 0.3 to 1.1mg%, F.W. at Noggkwang, 0.5~4.3mg%, F.W. at Chungyang. The ratios of capsaicin versus dihydrocapsaicin were 5.4:4.6 at Noggkwang and 7.5:2.5 at Chungyang. The important consumer acceptance factors according to situation are following that shape of green pepper (80%) at buying factor, deep green color (25.8%) at appearance factor, cultivar of green red pepper (21.8%) at eating factor. The interest in the cultivation area was relatively low(13.8%). It is considered that the color, appearance and spicy taste of variety as design factor of sorter, marking factor of package for distribution.