• 한국지능시스템학회논문지
• /
• 제11권9호
• /
• pp.822-826
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of 10 persons show that the proposed method yields high recognition rates.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.129-130
• /
• 2008

In this study, we implement the color image processing algorithm to analyze the quantitative assessment of denticulus by computing spectral characteristics in HGB color domain. We can observe that we can utilize the normalized HGB color feature to assess the quantitative formation of denticulus.

• 대한원격탐사학회지
• /
• 제15권3호
• /
• pp.183-194
• /
• 1999

위성에서 관측된 다중분광 위성영상 데이터를 이용목적에 따라 분석하고 활용하기 위해서는 영상 자체에 내포된 밝기, 칼라, 질감 등 다양한 특징들이 중요한 정보원으로 이용되고 있다. 특히 질감이나 칼라정보를 이용한 위성영상의 분석과정에서 가장 중요한 문제는 원 영상의 정보를 효율적으로 표현하는 속성을 추출하여 적절히 활용하는 것이다. 따라서 본 논문에서는 위성영상 분석에 유용하게 사용할 수 있는 6개의 속성 벡터들을 선정한 다음 SPOT 위성에서 관측된 영상을 이용하여 각각의 속성들에 대한 분별력을 평가하기 위하여 역전파 신경망(Back-propagation Neural Network)을 이용한 분류 네트워크를 구성하였고, 실험하고자 하는 지역에 대한 훈련집합 선택시 선정된 여섯 개이 속성 벡터들을 분류에 사용될 특징으로 선택하였다. 분류 실험을 수행한 결과 각각의 벡터 속성들은 개개의 특성에 따라 많은 장단을 내포하고 있었으며, 전반적으로는 비교적 정확한 분류결과를 나타내었다. 따라서 칼라 및 질감 속성 벡터들은 위성영상의 분류과정에 효과적으로 사용될 수 있음은 물론 다양한 영상분석 및 응용분야에서도 유용하게 이용될 수 있을 것으로 기대된다.

• 한국멀티미디어학회논문지
• /
• 제11권6호
• /
• pp.777-786
• /
• 2008

Human face avatar is important information in nowadays, such as describing real people in virtual world. In this paper, we have presented a face avatar creation and warping algorithm by using face feature analysis method, in order to detect face feature, we utilized local mean method based on facial feature appearance and face geometric information. Then detect facial candidates by using it's character in $YC_bC_r$ color space. Meanwhile, we also defined the rules which are based on face geometric information to limit searching range. For analyzing face feature, we used face feature points to describe their feature, and analyzed geometry relationship of these feature points to create the face avatar. Then we have carried out simulation on PC and embed mobile device such as PDA and mobile phone to evaluate efficiency of the proposed algorithm. From the simulation results, we can confirm that our proposed algorithm will have an outstanding performance and it's execution speed can also be acceptable.

• 한국컴퓨터그래픽스학회논문지
• /
• 제16권1호
• /
• pp.1-7
• /
• 2010

비전 기반의 감시 시스템에서 동일인의 식별은 매우 중요하다. 감시 시스템에서 주로 사용되는 CCTV 카메라의 영상은 상대적으로 낮은 해상도를 가지므로 얼굴 인식 기법을 이용하여 동일인을 식별하기는 어렵다. 본 논문에서는 CCTV 카메라 영상에서 의상 특징을 이용하여 동일인을 식별하는 알고리즘을 제안한다. 건물의 주출입구에서 출입자가 인증을 받을 때, 의상 특징이 데이터베이스에 저장된다. 그 후, 건물 내에서 촬영한 영상에 대해 배경 차감 및 피부색 발견 기법을 이용하여 의상 영역을 발견한다. 의상의 특징 벡터는 텍스처와 색상 특징을 이용하여 구성한다. 텍스처 특징은 지역적 에지 히스토그램을 이용하여 추출된다. 색상 특징은 색상 지도의 옥트리 기반 양자화(octree-based quantization)를 이용하여 추출된다. 건물 내의 촬영 영상이 주어질 때, 데이터베이스에서 의상 특징이 가장 유사한 사람을 발견함으로써 동일인을 식별하며, 의상 특징 벡터 간의 유사도 측정을 위해서는 유클리디안 거리(Euclidean distance)를 사용한다. 실험 결과, 얼굴인식 기법이 최대 43%의 성공률을 보인 데 비해, 의상 특징을 이용하여 80%의 성공률로 동일인을 식별하였다.

• Journal of Biosystems Engineering
• /
• 제37권4호
• /
• pp.252-257
• /
• 2012

Purpose: The net rind pattern and color of melon surface are important for a high market value of melon fruits. The development of the net and color are closely related to the changes in shape, size, and maturing. Therefore, the net and color characteristics can be used indicators for assessment of melon quality. The goal of this study was to investigate the possibility of estimating melon soluble solids content (SSC) and firmness by analyzing the net and color characteristics of fruit surface. Methods: The true color images of melon surface obtained at fruit equator were analyzed with 18 color features and 9 texture features. The partial least squares (PLS) method was used to estimate SSC and firmness in melons using their color and texture features. Results: In sensing melon SSC, the coefficients of determination of validation (${R_v}^2$) of the prediction models using the color and texture features were 0.84 (root mean square error of validation, RMSEV: 1.92 $^{\circ}Brix$) and 0.96 (RMSEV: 0.60 $^{\circ}Brix$), respectively. The ${R_v}^2$ values of the models for predicting melon firmness using the color and texture features were 0.64 (RMSEV: 4.62 N) and 0.79 (RMSEV: 2.99 N), respectively. Conclusions: In general, the texture features were more useful for estimating melon internal quality than the color features. However, to strengthen the usefulness of the color and texture features of melon surface for estimation of melon quality, additional experiments with more fruit samples need to be conducted.

• 한국멀티미디어학회논문지
• /
• 제9권8호
• /
• pp.982-999
• /
• 2006

본 논문에서는 복합 칼라정보와 얼굴의 기하학적 정보를 이용한 인터넷 기반 얼굴관상해석 및 자동 얼굴 컨텐츠 생성시스템을 제안하였다. 제안한 시스템은 YCbCr과 YIQ 칼라모델의 Cr과 I 성분의 논리곱 연산처리로 얼굴영역을 검출하였다. 검출한 얼굴영역에서 얼굴의 기하학적 정보로부터 얼굴 특징자를 추출 하였으며 각 특징자들을 세부 분류하여 얼굴 관상을 해석하도록 하였다. 또한 제안한 시스템은 추출과 분류된 특징자로부터 개인의 얼굴에 가장 적합한 얼굴 아바타 컨텐츠를 자동 생성할 수 있게 하였다. 실험결과 제안한 방법은 기존의 얼굴인식 방법에 비해 실시간 얼굴검출과 인식은 물론 정량적인 얼굴관상해석과 자동 얼굴 아바타 생성이 가능하였다.

• 복식
• /
• 제62권6호
• /
• pp.38-52
• /
• 2012

The purpose of this study is to confirm the international unique color sensibility according to the ethnic color preferences. The existing studies about color sensibility were investigated to analyze the international color sensibility. The countries were chosen according to its, strong regional and racial color. Also, the documents and websites about environment color such as structure color, natural feature color, traditional folk costume color and customary color names were investigated, and then, the international color sensibility was analyzed by using the color image scale. As a result of the analysis about the differences of color sensibility, internationally distinguished color sensibility was discovered. There were differences not only for the preference trend of hue but also for the tone or contrast of color among the selected countries. Especially, Great Britain had a strong preference for G categories that they preferred the warm-grayish color image. Russia has a preference for R, G, and B categories with the preference for the warm-clear image. Netherlands had a preference for R, Y, and PB categories and it preferred the cool-hard-grayish, warm-soft-clear image. Italy had a preference for R and Y categories and it preferred the warm-clear image. Morocco had a preference for R and B categories and it preferred the warm and cool, clear image. Japan had a preference for R, G categories and it preferred the warm-grayish image. Korea had a preference for R and B categories and it preferred the warm-soft-clear, and cool-clear image. With these results, the researcher concludes that the integrated analysis of the environment color and the traditional racial color factors are very persuasive methods to comprehend the international color sensibility.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권1호
• /
• pp.68-80
• /
• 2013

Lung cancer is considered to be the leading cause of cancer death worldwide. A technique commonly used consists of analyzing sputum images for detecting lung cancer cells. However, the analysis of sputum is time consuming and requires highly trained personnel to avoid errors. The manual screening of sputum samples has to be improved by using image processing techniques. In this paper we present a Computer Aided Diagnosis (CAD) system for early detection and diagnosis of lung cancer based on the analysis of the sputum color image with the aim to attain a high accuracy rate and to reduce the time consumed to analyze such sputum samples. In order to form general diagnostic rules, we present a framework for segmentation and extraction of sputum cells in sputum images using respectively, a Bayesian classification method followed by region detection and feature extraction techniques to determine the shape of the nuclei inside the sputum cells. The final results will be used for a (CAD) system for early detection of lung cancer. We analyzed the performance of a Bayesian classification with respect to the color space representation and quantification. Our methods were validated via a series of experimentation conducted with a data set of 100 images. Our evaluation criteria were based on sensitivity, specificity and accuracy.

• 한국실내디자인학회논문집
• /
• 제21권4호
• /
• pp.138-145
• /
• 2012

The epidermal color is one of factors the space for ages. Instead of the epidermal color expression, it made with material and decoration under structure for make shade of meaning before have the new media. But now a days, the epidermal color of the fashion store is getting free owe to the development of color harmony, has a great notion that gets out of the subordinate from color, and it is a emphasized factor with expression and self-control. The epidermal color of the fashion store makes an effort to accept the development and changing of new media. It should show that there role and function is changing constantly according to a new technology, and it gave a motivation for reanalysis about existence and expression of the epidermal color. The purpose of this research is that look around the feature of the epidermal color system, elements, and principle. Then contemporary fashion store is expressive characteristics of epidermal color. Using epidermal color is not common, we can find lots of the case with surface color, layer color, interface color, though. The paper reflects on the meaning and concept of fashion store which enables the application of expressive characteristics on space through advanced technology. Meanwhile, the features of epidermal color such as immateriality of process and communication can be inferred from case analysis.