• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.239-245
• /
• 2004

A hue-based noise-tolerant corner detector is proposed for the exact detection of the real corners in spite of the shadows and random noise. Based on the fact that the hue gradient at the border of the opaque objects' shadow is smaller than the intensity gradient in HSI (hue-saturation-intensity) color space, the effects of shadow are eliminated by introducing the hue-weighted combination of vector gradient to the proposed corner detector. Furthermore, the proposed corner detector is robust to random noise by offsetting the contribution to the corner candidate when the polarities of the color gradients of the pixel pairs are out of phase each other. Results of the experiment show that the proposed corner detector can effectively detect the real corners.

• Textile Coloration and Finishing
• /
• v.25 no.4
• /
• pp.241-246
• /
• 2013

The color properties of a white or nearly colorless fabric are represented by whiteness index (WI) or yellowness index (YI). These two indexes relate to a white fabric's color quality. The purpose of this study was to identify the properties of WI and YI on the CIELAB through the simulations of estimation data for a systemization of color quality control. The results indicated that the relationship between WI and YI was a negative correlation, however the coefficients of correlation function between WI and YI were depended on hue. There were two hue transition points of the rate of changes in WI and YI. These hue transition points were the reference points to divide the hue contribution to WI and YI. These points were not the point of h=0 and h=180 and asymmetric. In addition, where the colors were same distance from the white point on the CIELAB, the rate of changes in WI and YI by ${\Delta}$Ew were depending on hue. Specifically, when WI decreased, YI of reddish and yellowish tinted colors decreased more than bluish tinted colors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2417-2422
• /
• 2015

Mean-Shift tracking using hue has a problem that it fail in the object tracking when background has similar hue to the object. This paper proposes an improved Mean-Shift tracking algorithm using new data instead of a hue. The new data is generated by adaptive mixture of hue and saturation which have low interrelationship . That is, the proposed algorithm selects a main attribute of color that is able to distinguish the object and background well and a secondary one which don't, and places their upper 4 bits on upper 4 bits and lower 4 bits on the mixture data, respectively. The proposed algorithm properly tracks the object, keeping tracking error maximum 2.0~4.2 pixel and average 0.49~1.82 pixel, by selecting the saturation as the main attribute of color under tracking environment that background has similar hue to the object.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.16-25
• /
• 2009

In this paper we propose the block based image segmentation method using the cyclic properties of hue components in HSI color model. In proposed method we use center point instead of hue mean values as the hue representatives for regions in image segmentation considering hue cyclic properties and we also use directed distance for the hue difference among regions. Furthermore we devise the simple and effective method to get critical values through control parameter to reduce the complexity in the calculation of those in the conventional method. From the experimental results we found that the segmented regions in the proposed method is more natural than those in the conventional method especially in texture and red tone regions. In the simulation results the proposed method is better than the conventional methods in the in the evaluation of the human segmentation dataset presented Berkely Segmentation Database.

• Journal of Korean Ophthalmic Optics Society
• /
• v.13 no.4
• /
• pp.109-114
• /
• 2008

Purpose: To assess the reproducibility and repeatability for each color vision test method. Methods: The subjects for color vision test were 30 students without congenital color vision deficiency and they major in optometry in a university, Korea. The type of color vision test selected for this study were Hans color vision test, Hans 15 hue test and Lanthony D 15 hue test. The Ishihara test was added for assessment of reliability of inter-tester. Results: All of the subjects were classified into normal at pseudoisochromatic plates, but one subject's result showed mild blue-yellow color deficiency at Hue discrimination. Results of 3 repeated test for subjects and inter-tester examination showed no errors at pseudoisochromatic plates. There were differences in mild errors among repeated test at Hue discrimination, but no differences were found in the results of repeated test to classify color vision deficiency. Conclusion: Each tester had better be more skilled to test even simple color vision test for eliminating the possibility of mild errors. Each subject might just as well be careful in color vision test. It is required to test both method of pseudoisochromatic plates and Hue discrimination in screening test.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.2011-2025
• /
• 2021

In high-resolution satellite image classification, when the color values of pixels belonging to one class are different, such as buildings with various colors, it is difficult to determine the color information representing the class. In this paper, to solve the problem of determining the representative color information of a class, we propose a method to divide the color channel of HSV (Hue Saturation Value) and perform object-based classification. To this end, after transforming the input image of the RGB color space into the components of the HSV color space, the Hue component is divided into subchannels at regular intervals. The minimum distance-based image classification is performed for each hue subchannel, and the classification result is combined with the image segmentation result. As a result of applying the proposed method to KOMPSAT-3A imagery, the overall accuracy was 84.97% and the kappa coefficient was 77.56%, and the classification accuracy was improved by more than 10% compared to a commercial software.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.2
• /
• pp.1-10
• /
• 2010

There have been studied with activity about color standard due to extention of digital contents' application area. Therefore the studies in relation to the standard are needed to represent image's feature as color. Also the methods to extract color's feature to be apt to various application are needed. In this paper, we set the base color as 50 colors from Munsell color system, get the color histogram to show the characteristics of colors's distribution of a image, and propose the method to extract representative colors from the histogram. Firstly, we convert a input image of RGB color space to a image of HSI color space and split the image into hue area and non-hue area. To split hue area and non-hue area, we use a fixed threshold and a perception-function of color area function to reflect the subjective vision of human-being. We compute histograms from each area and then make a total histogram from the histogram of hue area and the histogram of hue area, and extract the representative colors from the histogram. To evaluate the proposed method, we made 18 test images, applied conventional methods and proposed method to them Also the methods are applied to public images and the results are analyzed. The proposed method represents well the characteristics of the colors' distribution of images and piles up colors' frequency to representative colors. Therefore the representative colors can be applied to various applications

• Korean Journal of Food Science and Technology
• /
• v.34 no.2
• /
• pp.164-169
• /
• 2002

Five kinds of red wine from three different grape varieties, such as Gerbong (G), Campbell (C), Moru (M), Gerbong+Moru (70:30, GM), and Gerbong+Campbell(70:30, GC) were prepared in the year of 2000. The total phenolic content and color changes were monitored using hunter colorimeter and spectrophotometry methods during wine processing. The total phenolic content of Gerbong (G), Campbell (C), Moru (M), Gerbong+Moru(70:30, GM), and Gerbong+Campbell(70:30, GC) were 712.6 mg/L, 3472.9 mg/L, 2209.4 mg/L, 2019.4 mg/L, and 1184.5 mg/L, respectively. Between total phenolic content and hunter colorimeter value (L, a, and b) of red wine showed no significant difference, but that of spectrophotometry color value (hue and intensity) were significantly different (p<0.001). The total phenolic content, hue, and intensity values represented significantly different between grape varieties (p<0.01, p<0.001). the hue showed a negative correlation relationship $(r^2=0.8660,\;p<0.0001)$, and that of intensity was a positive $(r^2=0.8304,\;p<0.0001)$ between total phenolic contents. The total phenolic content of red wine could be estimated simply using these equations, $Y_{Total\;phenolic\;content\;(mg/L)}=3319.3-X_{Hue}/2208.36,\;and\;Y_{Total\;phenolic\;content\;(mg/L)}=1230.97-X_{intensity}/98.93$

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.1
• /
• pp.63-71
• /
• 2003

This paper describes a color image segmentation algorithm based on region merging using hue difference as a restrictive condition. The proposed algorithm using mathematical morphology and a modified watershed algorithm does over-segmentation in the RGB space to preserve contour information of regions. Then, the segmentation result of color image is acquired by repeated region merging using hue differences as a restrictive condition. This stems from human visual system based on hue, saturation, and intensity. Hue difference between two regions is used as a restrictive condition for region merging because it becomes more important factor than color difference if intensity is not low. Simulation results show that the proposed color image segmentation algorithm provides efficient segmentation results with the predefined number of regions for various color images.

• Journal of Fashion Business
• /
• v.20 no.4
• /
• pp.1-14
• /
• 2016

Japan has several unique traditional colors. The traditional colors of Japan include a collection of colors used in traditional Japanese literature, textiles such as the kimono, and other Japanese arts. Japanese color system has a long history, leading to some consistencies in color and naming. During the Edo period(1603~1867), the unique color sense of 'iki' produced many color names that are often related to mouse(nezumi) and tea(cha), and fashion color originated as kabuki actors. As for colors named after animals, the most popular appears to be the mouse, which is used to express grey tones. Recently, many fashion companies in Japan have been working on reviving an interest in traditional Japanese colors. Ordinary people of Edo named even slightly different color tones, each with individual exquisite and mind valuing 'iki' senses. They translated these into their livelihood and culture. The colorimetry result of 49 restored dyed fabrics were as follows; Hue difference was 7.8, value difference was 2.9, chroma difference was 1.8 of prefix siro. Hue difference was 3.8, value difference was 1.6, chroma difference was 1.7 of prefix usu. Hue difference was 3.5, value difference was 1.5, chroma difference was 1.4 of prefix cha. Hue difference was 6.4, value difference was 1.1, chroma difference was 1.6 of prefix koi. Hue difference was 7.5, value difference was 0.8, chroma difference was 3.3 of prefix nezumi.