• Journal of Electrical Engineering and Technology
• /
• v.9 no.2
• /
• pp.707-720
• /
• 2014

This paper proposes a face tracking scheme that is a combination of a face detection algorithm and a face tracking algorithm. The proposed face detection algorithm basically uses the Adaboost algorithm, but the amount of search area is dramatically reduced, by using skin color and motion information in the depth map. Also, we propose a face tracking algorithm that uses a template matching method with depth information only. It also includes an early termination scheme, by a spiral search for template matching, which reduces the operation time with small loss in accuracy. It also incorporates an additional simple refinement process to make the loss in accuracy smaller. When the face tracking scheme fails to track the face, it automatically goes back to the face detection scheme, to find a new face to track. The two schemes are experimented with some home-made test sequences, and some in public. The experimental results are compared to show that they outperform the existing methods in accuracy and speed. Also we show some trade-offs between the tracking accuracy and the execution time for broader application.

• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.164-166
• /
• 2005

In this paper, using ranks of co-occurrence frequency about indices in neighboring pixels, we introduce a new re-indexing scheme for efficiency of index color image lossless compression. The proposed method is suitable for arithmetic coding because it has skewed distributions of small variance. Experimental results proved that the proposed method reduces the bit rates than other coding schemes, more specifically 15%, 54% and 12% for LZW algorithm of GIF, the plain arithmetic coding method and Zeng's scheme.

• Journal of Korea Multimedia Society
• /
• v.16 no.1
• /
• pp.1-10
• /
• 2013

This paper presents an approach for detecting and measuring human skin pigmentation. In the proposed scheme, we extract a skin area by a Gaussian skin color model that is estimated from the statistical analysis of training images and remove tiny noises through the morphology processing. A skin area is decomposed into two components of hemoglobin and melanin by an independent component analysis (ICA) algorithm. Then, we calculate the intensities of hemoglobin and melanin by using the location histogram and determine the existence of skin pigmentation according to the global and local distribution of two intensities. Furthermore, we measure the area and density of the detected skin pigmentation. Experimental results verified that our scheme can both detect the skin pigmentation and measure the quantity of that and also our scheme takes less time because of the location histogram.

• Korean Institute of Interior Design Journal
• /
• v.13 no.1
• /
• pp.70-80
• /
• 2004

The purpose of this study is to analyze the interior color characteristics of elderly housing facilities in U. S. A. For this purpose, a field survey was conducted between July 23 and July 31, 2003, visiting 10 elderly housing facilities in Contra Costa County, California. A three step analysis of the facilities involved. First, floor, walls, ceilings, base boards and doors in common spaces were examined for the color scheme using the "Pantone for Fashion and Home Color Guide" for each room. Measured Pantone numbers were converted to RGB color using "Chooser 3.0 of Pantone, Inc." Finally, the conversions were recorded as Munsell numbers. The results are as follows: First, the colors chosen for American elderly housing are high value and low chromatic colors. In many facilities, analogue colors such as BG, B, BP and Y, YR R, RP are used. Second, the colors of ceiling and wall are mainly very bright and low chromatic colors. The colors of floor are undertaking an Important role by generating major atmosphere in the America elderly housing. Third, the colors used for elderly housing are found inter-related. For example, the main color in the lobby is also used from corridor to stair and used again from lounge to dinning room as a secondary color. Fourth, it is found that accent colors are used at the beginning and end of stair and corridor outskirts in consideration of physical condition of elderly people. Fifth, there is no difference in color selection between elderly housing with low and high rental value. Preferably, more versatile colors are being chosen for elderly housing with the low rental value.he low rental value.

• 전자공학회논문지 IE
• /
• v.47 no.4
• /
• pp.53-58
• /
• 2010

In this paper we propose symbol decision method reflecting the color non-uniformity in 3-dimensional color space. By comparing with 2-dimensional color space decision method, we show the superiority of BER performance of the proposed method. Proposed method may reflect the non-uniformity since the symbol decision boundary in color space is transformed from 3D RGB space, and one dimension corresponding to Y value is added. Therefore, we can obtain the better BER performance by using the symbol decision method in 3D color space. In this paper, through numerical simulation, show the superior BER performance of 3D color space symbol decision method compared with 2D color space symbol decision method under AWGN and common mode noise channel.

• Fashion & Textile Research Journal
• /
• v.13 no.6
• /
• pp.838-847
• /
• 2011

The object of this study is as follows. First, according to the silhouette of clothes, I will search the relationship with the embroidery design. Second, I will investigate the relation of coloration about the clothes color and embroidery color. Third, I will search the relation with the image in clothes and embroidery design characteristic. The data acquisition is selected to the total 447 pictures of embroidery clothing design from the www.style.com, www.samsungdesign.net which are the related information site. The data are limited from S/S season in 2004 till F/W season in 2008 in the Paris, Milano, and New York collection. The analytical method was made through the analyze method and statistical method. First, on the relation with the clothes silhouette and embroidery design, if the satin stitch technique is utilized as the X-shaped or A-line silhouette in the one-piece and dress, the image which is elegant and feminine can be expressed. if the satin stitch technique is utilized as the H-line silhouette in jacket and court, the mannish image can be expressed. Second, the embroidery color showed up as the contrast combination of the monotone when the clothes color was the monochrome. And the embroidery color showed up as the tone in which is bright and sober when clothes color had 2 or 3 or 4. So, if the embroidery color is utilized as the similar color scheme, it will be effective. Third, if the embroidery technique of the one-piece and dress is utilized as the the satin stitch technique and the bloom and leaf motive being stylized pattern is used in the all-over and border pattern, It will be effective to express the romantic/feminine, ethnic/folklore, active, and classic image.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.394-400
• /
• 2012

SURF is a robust local invariant feature descriptor and has been used in many applications such as object recognition. Even though this algorithm has similar matching accuracy compared to the SIFT, which is another popular feature extraction algorithm, it has advantage in matching time. However, these descriptors do not consider relative location information of extracted interesting points to guarantee rotation invariance. Also, since they use gray image of original color image, they do not use the color information of images, either. In this paper, we propose a method for improving matching performance of SURF descriptor using the color and relative location information of interest points. The location information is built from the angles between the line connecting the centers of interest points and the orientation line constructed for the center of each interest points. For the color information, color histogram is constructed for the region of each interest point. We show the performance of our scheme through experiments.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3718-3726
• /
• 1999

Color image is more effective than gray one in human visual perception. Therefore, color image processing becomes important area. Color images are often corrupted by noises due to the input sensor, channel transmission errors and so on. Some filtering techniques such as vector median, mean filter, and vector $\alpha-trimmed$ mean filter have been used for color noise removal. Among them, vector $\alpha-trimmed$ mean filter gave the best performance in the mixed color noise. But, there are edge shift and blurring effect because vector $\alpha-trimmed$ mean filter is uniformly processed across the image. So, we proposed a conditional fuzzy cluster filter to improve this problems. Simulation results showed that the proposed scheme improves the NCD measure and visual quality over the conventional vector $\alpha-trimmed$ mean filter in the mixed color noise.

• International Journal of Contents
• /
• v.10 no.3
• /
• pp.9-16
• /
• 2014

Depth-image-based rendering is generally used in real-time 2D-to-3D conversion for 3DTV. However, inaccurate depth maps cause flickering issues between image frames in a video sequence, resulting in eye fatigue while viewing 3DTV. To resolve this flickering issue, we propose a new 2D-to-3D conversion scheme based on fast and robust depth-map generation from a 2D video sequence. The proposed depth-map generation algorithm divides an input video sequence into several cuts using a color histogram. The initial depth of each cut is assigned based on a hypothesized depth-gradient model. The initial depth map of the current frame is refined using color and motion information. Thereafter, the depth map of the next frame is updated using the difference image to reduce depth flickering. The experimental results confirm that the proposed scheme performs real-time 2D-to-3D conversions effectively and reduces human eye fatigue.

• Journal of Advanced Navigation Technology
• /
• v.10 no.1
• /
• pp.70-78
• /
• 2006

This paper has addressed the scheme to design single rate Rate Adaptive Shaper (srRAS) proposed in RFC2963. srRAS is the shaper used in conjugation with downstream single rate Three Color Marker (srTCM) described in RFC269. it is tail-drop First Input First Out (FIFO) queue that is drained at a variable rate. srTCM meters IP packet streams from srRAS and marks its packets to be either green, yellow, or red. This shaper has been proposed to use at the ingress of differentiated services networks providing AF PHB. And then srRAS can reduce the burstiness of the upstream traffic of srTCM. This paper addresses algorithm, architecture of srRAS, and the scheme to implement srRAS using Field-Programmable Gate Arrays (FPGA) and the related technology.