• 한국컴퓨터정보학회논문지
• /
• 제9권2호
• /
• pp.27-32
• /
• 2004

하나의 객체 내에 존재하는 영역들이 상이한 칼라의 집합으로 구성되어 있다면, 해당 객체는 독립적인 영역들로 분할되기 때문에 객체의 의미가 상실된다. 따라서 영역에 대한 칼라 정보 외에 다른 지식 정보를 선택적으로 적용할 수 있는 방법이 요구된다. 본 논문에서는 영상을 구성하는 색상 정보 외에 입체감을 표현하기 위한 방법으로 명암의 등가를 연결한 등조선의 형태분석을 이용하고 있다. 그리고 분석된 정보를 통해 영역간의 독립, 종속 여부를 판단하여 객체의 의미 있는 영역 정합을 통한 객체 분리의 방법을 제시하고 있다.

• Journal of the Optical Society of Korea
• /
• 제4권1호
• /
• pp.66-70
• /
• 2000

The main problem of image projection on a transmission type holographic screen is color sepa-ration. And it can be overcome by using a long narrow slit type diffuser as a source of the object beam when we record the screen. But that screen is not optimized and so needs changing several conditions. To set up the system many complicate things should be taken into accounted so it is very important to analyze the basic structure by simple concepts and calculations. We designed the system so that recording and projection axis coincide in one line and showed that the analysis of the system is very simple. We did it by a 1st order paraxial approximation calculation and it was good enough to describe the system. The photo-emulsion layer shrinks after processing of the hologram. It induced unsatisfactory color matching at the viewing zone. To overcome this effect, we pre-checked the shrinkage rate of an emulsion layer by experiments and modified the recording set up to compensate for the amount of shrinkage.

• 정보처리학회논문지B
• /
• 제15B권3호
• /
• pp.197-204
• /
• 2008

특정인을 추적하는 기술은 인간처럼 행동하는 로봇기술에서 가장 많이 등장하는 기술이다. 이 기술은 세 가지 영역에서 접근하고 있는데 첫 째가 특정인의 의상 색상이고 두 번째가 특정인의 얼굴과 그 표정이며 세 번째가 특정인의 제스처나 머리의 움직임이다. 그러나 로봇은 센서를 통해 색상이나 제스처를 감지할 수 있기 때문에 폐쇄회로 카메라를 통해 획득한 영상만으로 특정인을 추적하는 것과는 다르다. 폐쇄회로 카메라에서 가장 큰 문제점은 시스템 속도인데 입력된 영상에서 다시 계산에 의해 특정인을 추적하기위해서는 계산수를 줄여야한다. 시스템 속도를 높이기 위해 색상 추적은 통계치를 사용하는 것이 좋고 얼굴인식은 고유 얼굴을 사용하는 것이 바람직하다. 색상과 얼굴인식만으로는 추적에 어려움이 있기 때문에 모션 분석이 필요하다. 기존의 모션 분석이 주어진 영상의 전체 영역에서 형상을 바탕으로 이루어지기 때문에 속도가 느리고 인식률도 떨어진다. 본 논문에서는 얼굴 인식 시 찾아진 얼굴영역에 대한 모션분석을 계산속도가 빠른 운동에너지를 써서 인식률과 인식 속도를 높였다. 본 논문이 제안한 알고리즘과 Girondel, V. 등이 제시한 방법을 같은 동영상에서 실험한 결과 동일한 인식률을 얻었으며 인식속도는 제안한 알고리즘이 더 빨랐으며 LDA를 사용할 경우 속도는 비슷하나 인식률은 더 나은 결과를 얻었으며 특정인을 찾는 것은 제안한 알고리즘이 더 효과적이었다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.384-386
• /
• 1998

The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction(HCI). Many methods hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network(NN), Hidden Markov Model(HMM) and so on. In our research, a HMMs is proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin-color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and thus, produces a trajectory. The spotting a feature database, the proposed approach use the mesh feature code for codebook of HMM. In our experiments, 1300 alphabetical and 1300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfying recognition rate for the images with different sizes, shapes and skew angles.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.299-302
• /
• 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.

• 전자공학회논문지A
• /
• 제33A권5호
• /
• pp.203-211
• /
• 1996

This paper describes CAD tools for the construction of image database in IC chip analysis CAD system. For IC chip analysis by high-resolution microscopy, the image database is essential to manage more than several thousand images. But manual database construction is error-prone and time-consuming. In order to solve this problem, we develop a set of CAD toos that include image grabber to capture chip images, image editor to make the whole chip image database from the grabbed images, and image divider to reconstruct the database that consists of evenly overlapped images for efficient region search. we also develop an interactive pattern matching method for user-friendly image editing, and a heuristic region search method for fast image division. The tools are developed with a high-performance graphic hardware with JPEG image comparession chip to process the huge color image data. The tools are under the field test and experimental resutls show that the database construction time can be redcued in 1/3 compared to manual database construction.

• 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.

• 복식문화연구
• /
• 제16권2호
• /
• pp.293-304
• /
• 2008

The objectives of this study were to investigate the images in men's hairstyle by hair color, tone, texture, and perceiver's gender, and to examine the characteristics of hairstyle appropriate to seasons. A quasi-experimental method by questionnaire was used, and the experimental design was $4{\times}3{\times}2{\times}2$(hair color$\times$tone$\times$texture$\times$perceiver's$\times$gender) factorial design. The subjects were 372 men and women in their 20s through 50s. five factors of men's hairstyle image were derived by factor analysis: individuality, dignity, romanticism, refinement, and activity. Black hair was perceived to be high in dignity and activity. Bright tone was perceived to be high in individuality, but low in dignity. Men's wave hair was perceived to be higher in individuality than straight hair, but lower in dignity. Perceiver's gender did not give significant influence on evaluation of all image factors. In brown, neutral tone was perceived to be higher in dignity. romanticism, and activity than dark or bright tone. In black, wave hair was perceived to be more refined than straight hair. Black hair matches with winter the most, and yellow matches with spring the most. In terms of tone, dark tone matches with winter; neutral tone matches with autumn; bright tone matches with summer. The results of this study verified that hair color and texture affect men's image perception, and matching hair colors are associated with seasons.

• 한국컴퓨터정보학회논문지
• /
• 제7권4호
• /
• pp.46-51
• /
• 2002

본 논문은 얼굴 요소 중 눈썹을 검출하기 위한 기법으로, 눈썹은 얼굴 인식이나 표정 인식, 얼굴 애니메이션에 중요한 역할을 하는 요소이다. 색상 영역 분할을 통해 얼굴 영역을 검출한 다음, 형판 정합(template matching)을 통해 눈을 검출한다. 눈썹은 눈 바로 위에 위치하므로 검출된 눈의 위치 값을 이용하여 눈썹 후보 영역을 설정한다. 이렇게 설정된 눈썹 후보 영역에서 휘도(luminance) 성분의 히스토그램을 구한 다음, 이 히스토그램을 이용하여 thresholding 기법으로 눈썹을 검출한다. 일반적으로 이런 히스토그램은 하나의 bin을 갖는 peak나 valley가 무수히 많아 threshold 간을 결정하는데 어려움이 있다. 이런 어려움을 극복하고 좀더 쉽게 threshold 값을 찾기 위해 이런 peak나 valley를 제거해 히스토그램을 변형한다. 제안된 알고리즘은 얼굴 영역 검출부, 얼굴 요소 검출부, 그리고 FCP 추출부 등의 세 부분으로 구성되어있다.

• 통합자연과학논문집
• /
• 제11권3호
• /
• pp.131-138
• /
• 2018

In this paper, we have implemented speeches that utilized the emotion information of the user's speech and image matching and recommendation system. To classify the user's emotional information of speech, the emotional information of speech about the user's speech is extracted and classified using the PLP algorithm. After classification, an emotional DB of speech is constructed. Moreover, emotional color and emotional vocabulary through factor analysis are matched to one space in order to classify emotional information of image. And a standardized image recommendation system based on the matching of each keyword with the BM-GA algorithm for the data of the emotional information of speech and emotional information of image according to the more appropriate emotional information of speech of the user. As a result of the performance evaluation, recognition rate of standardized vocabulary in four stages according to speech was 80.48% on average and system user satisfaction was 82.4%. Therefore, it is expected that the classification of images according to the user's speech information will be helpful for the study of emotional exchange between the user and the computer.