• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.105-107
• /
• 2004

In this work, we suggested the method which improves the efficiency of the face detection algorithm using Pulse-Coupled Neural Network. Face detection algorithm which uses the color information is independent on size, angle, and obstruction of a face. But the use of color information encounters some problems arising from skin-tone color in the background, intensity variation within faces, and presence of random noise, and so on. Depending on these conditions, we obtained the mean and variance of skin-tone colors by experiments. Then we introduce a preprocess that the pixel with a mean value of skin-tone colors has highest level value(255) and the other pixels in the skin-tone region have values between 0 and 255 according to a normal distribution with a variance. This preprocess leads to an easy decision of the linking parameters.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2007.06a
• /
• pp.289-292
• /
• 2007

객체기반 영상분류를 위한 영상분할에 있어서 중요한 요소로는 분할축척(Scale), 분광 정보(Color), 공간 정보(Shape) 등이 있으며 공간 정보에 해당하는 공간 변수는 평활도(Smoothness)와 조밀도(Compactness)가 있다. 이들 가중치의 선택이 최종적으로 객체기반 영상분류의 결과를 좌우하게 된다. 본 연구는 객체기반 영상분류의 준비 과정이라 할 수 있는 영상분할에 있어서 다양한 가중치를 적용을 통하여 영상을 분할하였다. 영상분할을 위해 적용한 가중치는 10, 20, 30의 분할축척(Scale)과 분광 정보(Color)와 공간 정보(Shape)간의 가중치 조합, 공간 변수인 평활도(Smoothness)와 조밀도(Compactness)간의 가중치 조합을 사용하였다. 각 가중치 조합을 통하여 분할된 영상의 분석은 Moran's I 와 객체 내부 분산(Intrasegment Variance)을 이용하여 분석하였다. 각 객체간의 상관관계 분석을 위하여 Moran's I를 계산하였으며 분류된 지역의 동질성을 분석하기 위하여 객체 면적을 고려한 객체 내부 분산(Intrasegment Variance)값을 계산하였다. Moran's I 가 낮은 값을 가질수록 객체 간의 공간상관관계가 낮아지므로 이웃 객체간의 이질성은 높아지며 객체 내부 분산(Intrasegment Variance)이 낮은 값을 가질수록 지역간의 동질성은 높아지게 된다. Moran's I 와 객체 내부 분산(Intrasegment Variance)의 조합을 통하여 객체기반 영상분류 시 가장 높은 분류 정확도가 예상되는 밴드별 영상분할 가중치를 얻을 수 있다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.101-110
• /
• 1996

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 224 colors with 256 or less colors, called color palette. In this paper, we propose an algorithm to design the 256 or less size color palette by using spatial maskin geffect of HVS and subjective distortion measure weighted by color palette by using spatial masking effect of HVS and subjective distortion measure weighted by color activity in 4*4 local region in any color image. The proposed algorithm consists of octal prequantization and subdivision quantization processing step using the distortion measure and modified Otsu's between class variance maximization method. The experimental results show that the proposed algorithm has higher visual quality and needs less consuming time than conventional algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1048-1052
• /
• 2004

In this work, we have investigated a role of linking parameter in Pulse-Coupled Neural Network(PCNN) which is suggested to explain the synchronous activities among neurons in the cat cortex. Then we have found a method to determine the linking parameter for a satisfactory face detection performance in a given color image. Face detection algorithm which uses the color information is independent on pose, size and obstruction of a face. But the use of color information encounters some problems arising from skin-tone color in the background, intensity variation within faces, and presence of random noise and so on. Depending on these conditions, PCNN's linking parameters should be selected an appropriate values. First we obtained the mean and variance of the skin-tone colors by experiments. Then, we introduced a preprocess that the pixel with a mean value of skin-tone colors has the highest level value (255) and the other pixels have values between 0 and 255 according to normal distribution with a variance. This preprocessing leads to an easy decision of the linking parameter of the Pulse-Coupled Neural Network. Through experiments, it is verified that the proposed method can improve the face detection performance compared to the existing methods.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.27 no.2
• /
• pp.188-199
• /
• 2003

This study intended to analyze the differences in (general & apparel) color preference and possession of apparel color preference(POA) by influential factors(fashion involvement, age, body-size and body- cathexis). We collected data from 303 females in the ages of 20's and 40's living in Seoul. The results were as follows; As a result of factor analysis, the fashion involvement was categorized into three aspects: coordinating fashion involvement, opinion-leading fashion involvement, and innovating fashion involve ment. There were significant differences among fashion involvement groups in the color preference and POA. Also the significant differences in color preferences and POA by ages and body-size were found. But in the analysis based on body-cathexis, no noticeable variance between different groups were found.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.1
• /
• pp.125-133
• /
• 2017

Color in an image is determined by illuminant and surface reflectance. So, to recover unique color of object, estimation of exact illuminant is needed. In this study, the illumination models suggested to get the object color constancy with the physical illumination model based on physical phenomena. Their characteristics and application limits are presented and the necessity of an extended illumination model is suggested to get more appropriate object colors recovered. The extended illumination model should contain an additional term for the ambient light in order to account for spatial variance of illumination in object images. Its necessity is verified through an experiment under simple lighting environment in this study. Finally, a reconstruction method for recovering input images under standard white light illumination is experimented and an useful method for computing object color reflectivity is suggested and experimented which can be induced from combination of the existing illumination models.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.125-132
• /
• 2012

This paper proposes an automatic object segmentation and background composition method for video communication over consumer mobile phones. The object regions were extracted based on the motion and color variance of the first two frames. To combine the motion and variance information, the Euclidean distance between the motion boundary pixel and the neighboring color variance edge pixels was calculated, and the nearest edge pixel was labeled to the object boundary. The labeling results were refined using the morphology for a more accurate and natural-looking boundary. The grow-cut segmentation algorithm begins in the expanded label map, where the inner and outer boundary belongs to the foreground and background, respectively. The segmented object region and a new background image stored a priori in the mobile phone was then composed. In the background composition process, the background motion was measured using the optical-flow, and the final result was synthesized by accurately locating the object region according to the motion information. This study can be considered an extended, improved version of the existing background composition algorithm by considering motion information in a video. The proposed segmentation algorithm reduces the computational complexity significantly by choosing the minimum resolution at each segmentation step. The experimental results showed that the proposed algorithm can generate a fast, accurate and natural-looking background composition.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.225-232
• /
• 2009

In this paper, a new face detection method based on pupil color distribution maps with the frequency under the illumination variance is proposed. Face-like regions are first extracted by applying skin color distribution maps to a color image and then, they are reduced by using the standard deviation of chrominance components. In order to search for eye candidates effectively, the proposed method extracts eye-like regions from face-like regions by using pupil color distribution maps. Furthermore, the proposed method is able to detect eyes very well by segmenting the eye-like regions, based on a lighting compensation technique and a segmentation algorithm even though face regions are changed into dark-tone due to varying illumination conditions. Eye candidates are then detected by means of template matching method. Finally, face regions are detected by using the evaluation values of two eye candidates and a mouth. Experimental results show that the proposed method can achieve a high performance.

• The Journal of Advanced Prosthodontics
• /
• v.7 no.5
• /
• pp.400-405
• /
• 2015

PURPOSE. The purpose of this study is to mix dental ceramic powder in varying ratios and evaluate the effect of the mixing ratio on color and translucency. MATERIALS AND METHODS. The ceramic powder of shade A3 of the same product was mixed with the shade A2 of three products: IPS e.max Ceram (Ivoclar Vivadent, Schaan, Liechtenstein), Vintage Halo (SHOFU Inc., Kyoto, Japan), and Ceramco 3 (Ceramco-Dentsply, Burlington, NJ, USA) in the following fixed ratios (0 wt%, 25 wt%, 50 wt%, 75 wt%, and 100 wt%) and then fired. A total of 150 specimen of ceramic fired were manufactured in a regular size (W: 8.5 mm, L: 10.5 mm, and H: 1.5 mm). For color and translucency, $L^*$, $a^*$, and $b^*$ were measured and Two-way analysis of variance (ANOVA) and One-way analysis of variance (ANOVA) were used for data analysis (${\alpha}$=0.05). RESULTS. The higher the mixing ratio was, $L^*$, $a^*$, and $b^*$ of IPS e.max Ceram were all increased, and $L^*$ of Vintage Halo was reduced and $a^*$ and $b^*$ were increased. $L^*$ and $a^*$ of Ceramco3 were reduced and $b^*$ of Ceramco3 was increased. Color difference (${\Delta}E^*ab$) was increased in all three products as the mixing ratio got higher. Increased mixing ratios resulted in decreased translucency parameter (TP) values for IPS e.max Ceram but increased TP values for Vintage Halo and Ceramco3. CONCLUSION. In this limited study, CIE $L^*$, $a^*$, and $b^*$ were influenced by the mixing ratio of the A3 powders and porcelain powder mixtures represented a various color and translucency.

• Journal of the Korean Dietetic Association
• /
• v.17 no.4
• /
• pp.378-386
• /
• 2011

To examine the effect of obesity on volume perception according to size and color of rice bowl, we divided female college students into a normal weight group (<30% fat mass, n=100) and obese group (${\geq}30%$ fat mass, n=83) and then measured perceived volume of rice bowls of various sizes (general size; 350 ml vs. small size; 188 ml) and color (yellow, white, blue, and black) containing the same amount of cooked white rice (210 g). Normal weight group perceived that the general rice bowl contained significantly more cooked white rice compared to the small rice bowl. In contrast, the obese group perceived that the general rice bowl contained significantly less cooked white rice than the small rice bowl. The estimated variance in perceived volume of both bowls was significantly bigger in the obese group compared to the normal group. There were no differences in perceived volume among any of the subjects (both normal and obese groups) according to rice bowl color. However, the estimated variance in perceived volume in the obese group was significantly larger than that in the normal group for all of the rice bowls. In conclusion, rice bowl size and color might affect volume perception, and volume perception in obese people may be different from that of normal weight people.