• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.86-97
• /
• 2011

This paper presents a novel algorithm to detect more accurate road lane with image sensor-based color classification and directional edge clustering. With treatment of road region and lane as a recognizable color object, the classification of color cues is processed by an iterative optimization of statistical parameters to each color object. These clustered color objects are taken into considerations as initial kernel information for color object detection and recognition. In order to improve the limitation of object classification using the color cues, the directional edge cures within the estimated region of interest in the lane boundary (ROI-LB) are clustered and combined. The results of color classification and directional edge clustering are optimally integrated to obtain the best detection of road lane. The characteristic of the proposed system is to obtain robust result to all real road environments because of using non-parametric approach based only on information of color and edge clustering without a particular mathematical road and lane model. The experimental results to the various real road environments and imaging conditions are presented to evaluate the effectiveness of the proposed method.

• International Journal of Costume and Fashion
• /
• v.8 no.2
• /
• pp.50-64
• /
• 2008

The purpose of this study is to classify Avatar fashion style through analysis of on-line Avatar Mall and to propose color pallette and fashion contents from fashion color analysis. The literature research focused on investigating the notion, characters and types of Avatar and relation of Avatar and self-image, clothing image and color image. In data research, 4 on-line portal sites Avatar Malls were analyzed and Avatar fashion style was classified. In addition, Avatar clothing color was analyzed. The research of this study are as follows: Firstly, Avatar in the cyber space represents 'me' of the real states. Avatar fashion helps to represent Avatar Image and clothing makes human image and identity as a social sign. Color helps to constitute clothing impression and human image, therefore clothing and color are the important elements to express self-image through Avatar in the cyber space. Secondly, Avatar Malls of 4 on-line portal sites are very similar and confuse Avatar users because of no standard of fashion style classification. Accordingly, the standard of fashion style classification should be made by a fashion expert, and the specific characters of every on-line portal site should be emphasized. Thirdly, as a result of the analysis of Avatar's clothing, the clothing is divided into a real world clothing and an imaginary world clothing. There are daily clothes, uniform, event clothes, story clothes and fantasy clothes. As a result of the color analysis of Avatar clothing, White, Red, Red Purple colors and bright and vivid tone are generally used for Avatar clothing. This study is significant to classify Avatar fashion style systematically, to notify sensitive and delicate users' sign and to make Avatar fashion image emotional and high-quality.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.8
• /
• pp.70-75
• /
• 2003

It is very important to inspect the color of printed texture in the textile process. The standard colorimetric system used for the recognition of the color in the textile industry. It uses XYZ color system defined by CIE (Commission Internationale de 1Eclairage), but is too expensive. Therefore, in this paper, we propose a color inspection system of the printed texture using a color scanner. Because the scanner uses RGB value for color, it is necessary the mapping from RGB to XYZ. However, the mapping is not simple, and the scanner has even positional deviation because of the geometric characteristics. To transform from RGB to XYZ, we used a NN (neural network) model and also compensated the positional deviation. In real experiments, we could get fairly exact XYZ value from the proposed color inspection system in spite of using a color scanner with large measuring area.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.218-221
• /
• 2000

In this paper, we propose a new algorithm to detect human faces for controling a camera used in video conference. We model the distribution of skin color and set up the standard skin color in YIQ color space. An input video frame image is segmented into skin and non-skin segments by comparing the standard skin color and each pixels in the input video frame. Then, shape filler is applied to select face segments from skin segments. Our algorithm detects human faces in real time to control a camera to capture a human face with a proper size and position.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.15-18
• /
• 2001

Recently, CMOS image sensor is rapidly used as an image capture device such as mobile phone or notebook PC. Because of poor quality of image by CMOS image sensor, ISP is essential step to improve image quality. In this paper, we implemented and simulated ISP algorithm for real time moving picture of CMOS image sensor. Especial Iy, we concentrated on color interpolation, which extracts three color component from uncompleted color information. Several algorithms for color interpolation are implemented and analyzed to acquire a good quality of picture. Finally, we proposed an improved algorithm and confirmed the effectiveness by experimental simulation results.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.14 no.2
• /
• pp.1-20
• /
• 1996

we describes a method for realizing the color conversion from the tristimulus (X, Y, Z) values to the print ink signals (C, M, Y) by using neural networks. The realized nonlinear color conversion system consists of two hidden layers those have seventeen nodes. We determined the C, M, Y values of the input control signals to compensate the printer nonlinearity of real systems. Experimental results showed that the described method is useful and valid to realized the nonlinear color conversion.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.49.1-49
• /
• 2001

The skin color model is a very important concept in face detection, face recognition and face tracking. Usually, this model is obtained by estimating a probability density function of skin color distribution. In many cases, it is assumed that the underlying density function follows a Gaussian distribution. In this paper, a new method for non-parametric estimation of the probability density function, by using feed-forward neural network, is used to estimate the underlying skin color model. By using this method, the resulting skin color model is better than the Gaussian estimation and substantially approaches the real distribution. Applications to face detection and face ...

• Journal of Digital Convergence
• /
• v.13 no.9
• /
• pp.183-189
• /
• 2015

In this paper, we propose an object tracking method using the color information of the image in surveillance network. This method perform a object detection using of adaptive color model. Object contour detection plays an important role in application such as object recognition. Experimental results demonstrate successful object detection over a wide range of object's variation in color and scale. In applications to detect an object in real time, when transmitting a large amount of image data it is possible to find the mode of a color distribution. The specific color of an object is modified at dynamically changing color in image. So, this algorithm detects the tracking area information of object within relevant tracking area and only tracking the movement of that object.Through experiments, we show that proposed method is more robust than other methods under certain ideal situations.

• Korean Journal of Optics and Photonics
• /
• v.12 no.6
• /
• pp.452-459
• /
• 2001

ICC profiles of output devices are necessary to solve the problem of color inconsistency between output devices. Therefore, output device manufacturers are offering ICC profiles that encode each model\`s color characteristics according to the specification decided in ICC (International Color Consortium). In this study, a program that can decode data of ICC profile was composed and evaluated the present condition of ICC profile files of domestic CRT monitor. As a result of comparing the ICC profiles of various model\ulcorner selling since 1999 from LG and Samsung companies, it was found that ICC profiles that are made at a similar time are the same regardless of model\`s specification and in some profiles, extraordinary data are saved. Accordingly, it can be said that current ICC profiles are made independently of the real monitor\`s color characteristics. This paper shows how color characteristics of a real monitor are affected by the control of brightness and color temperature, and proposes that the ICC profile has to be made from the data. measured in the optimum brightness state at each color temperature setting.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.491-500
• /
• 2002

In this paper, we propose a real-time face detection and recognition system by using skin color informations, geometrical feature vectors of face, and facial angle informations from color face image. The proposed algorithm improved face region extraction efficiency by using skin color informations on the HSI color coordinate and face edge information. And also, it improved face recognition efficiency by using geometrical feature vectors of face and facial angles from the extracted face region image. In the experiment, the proposed algorithm shows more improved recognition efficiency as well as face region extraction efficiency than conventional methods.