• Journal of KIISE:Software and Applications
• /
• v.32 no.6
• /
• pp.523-531
• /
• 2005

Existing methods for color image segmentation using diffusion can't preserve contour information, or noises with high gradients become more salient as the number of times of the diffusion increases, resulting in over-segmentation when applied to watershed. This paper proposes a method for color image segmentation by applying morphological operations together with nonlinear diffusion For an input image, transformed into LUV color space, closing by reconstruction and nonlinear diffusion are applied to obtain a simplified image which preserves contour information with noises removed. With gradients computed from this simplified image, watershed algorithm is applied. Experiments show that color images are segmented very effectively without over-segmentation.

• Archives of design research
• /
• v.17 no.3
• /
• pp.27-38
• /
• 2004

It is important for designers to be supported with their decision-making on colours which is often based on personal distinction rather than logical dialogue that may lead to confusion within communicating with others. To help these problems and to gain productivity, we would like to propose a way to define colour grouping method. In other words, the purpose of this study is to help to improve the communication and productivity within the design and designers. The grouping was based and inspired by from the studies of Kobayashi, Hideaki Chijiawa, Allis Westgate and Martha Gill. The study of grouping is based on the "tones" of each group, as they seem to reflect a designer s sentimentalism of chosen colours the best. Each of these groups will be named Bright , Pastel ,Deep and Neutral The general concept of each groups are: - Bright: high quality of pixels of primary colour - Pastel: primary colour with white - - Deep: Primary colour with gray or black - Neutral: colours that does not include any of above Each of the colour group has been allocated into Si-Hwa Jung's colour charts and colour prism to visualize the relationships between the colour groups. These four groups and the colours included in them will be broken down to smaller groups in order to make colour palette. This would break the barrier and result in using colours in groups as well as crossover coordination. This study would result in new ways of using colurs for designers designers

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.25-36
• /
• 2008

In this paper, we present a robust hand recognition approach to sudden illumination changes. The proposed approach constructs a background model with respect to hue and hue gradient in HSI color space and extracts a foreground hand region from an input image using the background subtraction method. Eighteen features are defined for a hand pose and multi-class SVM(Support Vector Machine) approach is applied to learn and classify hand poses based on eighteen features. The proposed approach robustly extracts the contour of a hand with variations in illumination by applying the hue gradient into the background subtraction. A hand pose is defined by two Eigen values which are normalized by the size of OBB(Object-Oriented Bounding Box), and sixteen feature values which represent the number of hand contour points included in each subrange of OBB. We compared the RGB-based background subtraction, hue-based background subtraction and the proposed approach with sudden illumination changes and proved the robustness of the proposed approach. In the experiment, we built a hand pose training model from 2,700 sample hand images of six subjects which represent nine numerical numbers from one to nine. Our implementation result shows 92.6% of successful recognition rate for 1,620 hand images with various lighting condition using the training model.

• Korean Institute of Interior Design Journal
• /
• no.23
• /
• pp.19-25
• /
• 2000

This study aims by analysing the interior design elements trends of current medium size office buildings in Seoul. The analysing objects are ceiling, floor, wall, and illumination plan of current office buildings. Analysing tools are finishing material and color of each part. Analysing areas are lobby area, deskwork area, conference area, welfare area, public area(rest room, corridor, stair). The interior design elements of lobby shows a lots of different features then the other areas in ceiling, floor, and wall design. Such difference appears at finishing material especially, and the coloring is more splendorous then the other areas. Desk work area and conference area have similar characteristics in finishing materiors and colors, and they usually follow the needs of function. Walfare area shows more splendorous feature then deskwork and conference area, and designed by various materials and colors. Public area also shows very active design concept then past times.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.532-534
• /
• 2000

복합적인 감성기반 영상 검색 시스템을 구축하기 위해서는 감성속성으로 영상을 찾는 검색은 물론이고, 주어진 영상의 감성특성을 알아내는 과정이 필요하다. 본 논문에서는 영상의 특성으로부터 감성을 매핑하는 신경망을 구축하고 다양한 실험으로 그 가능성을 보인다. 여기에서 영상특징으로 웨이블렛계수와 위치정보를 사용했고, 감성공간으로는 SD법으로부터 14개의 형용사쌍을 추출했다. 이 두 공간의 매핑에 사용된 신경망의 입력으로 영상에서 얻은 RGB 색상당 36개의 총 108개의 웨이블렛 개수를 사용했고, 출력은 14개의 감속속성당 7등급으로 총 98개로 구성했다. 총 6명이 영상을 보고 평가한 감성평가데이터중에서 2명이 각각 평가한 데이터로 신경망을 학습시키고 나머지 10개로 테스트한 경우는 90%이상의 인식률을 보였다. 4명이 각각 90개씩 평가한 데이터로 신경망을 학습시키고 나머지 10개로 테스트한 경우는 90%의 인식률을 보였다. 또한 공통된 감성을 신경망을 통해 인식할 수 있는지 판단하기 위해 600개씩 2명으로부터 얻은 1200개의 데이터에 대해서 1000개를 학습시키고 200개를 테스트하고, 100개씩 4명으로부터 데이터에 대해서 360개를 학습시키고 40개를 테스트해 본 결과, 전자의 경우 오류율 8, 후자의 경우 0.7~0.8 범위였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.580-583
• /
• 2010

본 논문에서는 동영상을 대상으로 하는 시각 주의 탐색에 대한 새로운 시스템에 대하여 설명한다. 제안하는 시스템은 기존의 공간 주의 모델에 새로운 시간 특징 추출 모듈을 추가함으로써 색상 및 명암, 형태, 방위와 같은 공간 특징 외에 움직임과 같은 시간 특징을 추가로 사용한 시각주의 탐색 모델이다. 기존 시스템과 가장 큰 차이점으로 공간 특징의 가중치 결합 방법과 움직임 특징 추출방법, 공간과 시간 특징 간 결합방법에 있다. 시스템의 성능평가를 위하여 다양한 환경의 영상을 대상으로 실험하였고 제안하는 시스템은 영상에서 사람이 시각적으로 중요하게 인지하는 영역과 부합되는 결과를 보였다.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.103-110
• /
• 2005

In this paper, we present a shadow detection algorithm using the shadow features which appear in color images. Shadow regions have lower luminance and saturation than those of nearby regions, and is generally shown as dark colors. The regions are detected by means of analysing and applying their properties to images represented as the HSI color model. The proposed algorithm is consisted of two steps: at the first step, the candidate regions of shadow are found with using shadow features, and then, real shadow regions are detected only in candidate regions by using their information to reduce real objects and dark marks. The experimental results show that the algorithm is effective.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.7
• /
• pp.520-523
• /
• 2009

There are many ways to judge whether the input image is adult-image or not. Until now, adult image detection has been examined by the ratio of skin area in full image. In this paper, we propose a method to extract skin region in YCbCr. Skin region shows unique distribution in YCbCr, and we will separate the skin region from background using the distribution. First, we are going to find Eye zone using Eye-Map. Then we will find out the color value for the distribution of skin region using the color of Eye zone. Next, we will find the distribution of the area through the skin region in full-image.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.140-145
• /
• 2009

Significant attention has recently been drawn to human robot interaction system that uses face detection technology. The most conventional face detection methods have applied under pixel domain. These pixel based face detection methods require high computational power. Hence, the conventional methods do not satisfy the robot environment that requires robot to operate in a limited computing process and saving space. Also, compensating the variation of illumination is important and necessary for reliable face detection. In this paper, we propose the illumination invariant face detection that is performed under the compressed domain. The proposed method uses color balancing module to compensate illumination variation. Experiments show that the proposed face detection method can effectively increase the face detection rate under existing illumination.

• Journal of Advanced Navigation Technology
• /
• v.13 no.5
• /
• pp.773-780
• /
• 2009

This study proposed a face region detection algorithm using fuzzy inference of pixel hue and intensity. The proposed algorithm is composed of light compensate and face detection. The light compensation process performs calibration for the change of light. The face detection process evaluates similarity by generating membership functions using as feature parameters hue and intensity calculated from 20 skin color models. From the extracted face region candidate, the eyes were detected with element C of color model CMY, and the mouth was detected with element Q of color model YIQ, the face region was detected based on the knowledge of an ordinary face. The result of experiment are conducted with frontal face color images of face as input images, the method detected the face region regardless of the position and size of face images.