• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.147-149
• /
• 2004

There are no authentic solutions in a face region extraction problem though it is an important part of pattern recognition and has diverse application fields. It is not easy to develop the facial region extraction algorithm because the facial image is very sensitive according to age, sex, and illumination. In this paper, to solve these difficulties, a fuzzy color filer based on the facial region extraction algorithm is proposed. The fuzzy color filter makes the robust facial region extraction enable by modeling the skin color. Especially, it is robust in facial region extraction with various illuminations. In addition, to identify the fuzzy color filter, a linear matrix inequality(LMI) optimization method is used. Finally, the simulation result is given to confirm the superiority of the proposed algorithm.

• The Korean Journal of Food And Nutrition
• /
• v.10 no.2
• /
• pp.241-245
• /
• 1997

In order to make natural food color from Gardenia, we investigated optimal conditions of color extraction, and thermal stability and light stability of color extracted compared with Yellow-4. In case of ethanol extraction, optimal conditions for color extraction were substrate 10%, 4$0^{\circ}C$, pH 7.0 and 42rs, respectively. In case of water extraction, optimal conditions for color extraction were substrate 10%, 7$0^{\circ}C$, pH 7.0 and 48hrs, respectively. Extraction yield in the optimal conditions was 75% in ethanol and 63% in water. The thermal stability and light stability of Yellow-4 were both upper 98%, but those of Gardenia yellow color were 62 and 90%, respectively.

• The Korean Journal of Food And Nutrition
• /
• v.11 no.1
• /
• pp.68-71
• /
• 1998

In order make natural food color from gardenia(Gardenia jasminoides), we investigated optimal conditions of color extraction, in case of water extraction, optimal conditions for color extraction were 7$0^{\circ}C$, 48hrs, pH 7.0 and substrate 10%, respectively. And extracted crude color was purified by activated white clay, were isolated glycoside peak (238nm) and yellow color peak(40nm) from extracted crude color. The pruified color was increased by 27-fold and the yield was 96%.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.30 no.3
• /
• pp.466-470
• /
• 2001

Response surface methodology was used for monitoring extraction conditions, based on quality properties of old pumpkin extracts. Hunter's color L value of extracts was maximized at 101℃, 2.6 hr and decreased gradually after maximum point. The polynomial equation for Hunter's color L value showed 10% of significance level and 0.8799 of R². Hunter's color a value was minimized at 117℃, 3.9 hr and R² of polynomial equation was 0.9852 within 1% significance level. Hunter's color b value and ΔE value increased as the extracting temperature and time increased. Extraction yield of old pumpkin was maximized at 110℃, 4 hr and increased in proportional to the extracting temperature and time, but decreased after 113℃ and 2 hr. Viscosity of pumpkin extracts were maximized at 120℃, nearly 3 hr. R² of polynomial equations for yield, viscosity and sugar content were 0.9532, 0.9812 and 0.8869, respectively. Optimum ranges of extraction conditions for quality properties of old pumpkin were 102∼109℃, 2.5∼3.5 hr, respectively. Predicted values at the optimum extraction condition agreed with experimental values.

• Smart Media Journal
• /
• v.2 no.1
• /
• pp.31-36
• /
• 2013

A robust and efficient text extraction is very important for an accuracy of Optical Character Recognition (OCR) systems. Natural scene images with degradations such as uneven illumination, perspective distortion, complex background and multi color text give many challenges to computer vision task, especially in text extraction. In this paper, we propose a method for extraction of the text in signboard images based on a combination of mean shift algorithm and weighting scheme of hue and saturation in HSI color space for clustering algorithm. The number of clusters is determined automatically by mean shift-based density estimation, in which local clusters are estimated by repeatedly searching for higher density points in feature vector space. Weighting scheme of hue and saturation is used for formulation a new distance measure in cylindrical coordinate for text extraction. The obtained experimental results through various natural scene images are presented to demonstrate the effectiveness of our approach.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.28 no.5
• /
• pp.1087-1091
• /
• 1999

Microwave extraction system equipped with closed vessels, which is known to rapidly extract target compounds from natural products, was applied to monitor the changes in phenolic compounds, browning color intensity and electron donating ability by using response surface methodology(RSM). Maximum content of phenolic compound was 21.65mg/100ml in 67.88% of ethanol concentration, 145oC of extraction temperature, and 6.24min of extraction time. The phenolic compounds in extracts are dependent on the increase of the extraction temperature and the ethanol concentration. Browning color intensity, which was maximized in 67.21%, 147oC, and 6.02min, was proportional to the increase of the extraction temperature. Maximum value of electron donating ability was 24.50units in 54.33%, 147oC, and 6.11 min. The electron donating ability of extracts was dependent on the increase of extraction temperature and maximized in the range from 50 to 65% of ethanol concentration.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2331-2334
• /
• 2003

Generally, skin color information has been widely used at the face region extraction step of the face region recognition process. But many experimental results show that they are very sensitive to the given threshold range which is used to extract the face regions at the input image. In this paper, we propose a face region extraction algorithm based on an adaptive range decision for skin color. First we extract the pixels which are regarded as the candidate skin color pixels by using the given range for skin color extraction. Then, the ratio between the total pixels and the extracted pixels is calculated. According to the ratio, we adaptively decide the range of the skin color and extract face region. From the experiment results for the various images, the proposed algorithm shows more accurate results than the conventional algorithm.

• Journal of Fashion Business
• /
• v.13 no.2
• /
• pp.136-144
• /
• 2009

The purpose of this study is to investigate various phenomena quantitatively occurring during the course of changing dyeing conditions of cotton and silk fibers in natural dyeing using Caesalpinia sappan. Paying attention to the fact that the color may be varied according to the extraction conditions of dyestuffs in Caesalpinia sappan dyeing, the color changes were investigated after dyeing using dyestuffs extracted at elevated temperature and dyestuffs extracted at room temperature. According to the extraction methods, the degree of color development for the category of red color and the category of yellow color has changed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.4
• /
• pp.346-352
• /
• 2011

This paper presents a system of road extraction for traffic images from a single camera. The road in the images is subject to large changes in appearance because of environmental effects. The proposed system is based on the integration of color correlograms and random forest. The color correlogram depicts the color properties of an image properly. Using the random forest, road extraction is formulated as a learning paradigm. The combined effects of color correlograms and random forest create a robust system capable of extracting the road in very changeable situations.

• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.