• 한국의류학회지
• /
• 제24권1호
• /
• pp.24-33
• /
• 2000

The purpose of this study was to investigate the characteristic and image of oriental costume design on represented among three countries, Korea, China and Japan. The specific objectives were; 1) to identify the design characteristics of oriental costume. 2) to investigate the hierarchic structure of oriental costume image and the meaning structure of oriental costume image. The stimulus were 75 costume design of contemporary costume which represented the traditional image of orient. The main survey of questionary consisted of their evaluation of the oriental costume image by 26 semantic differential bi-polar scales and the subjects were 99 female students majoring in clothing and textiles. The data were analyze by Cluster analysis. Factor analysis, ANOVA, Scheffe test. The major findings were as follows; 1) As a result of design analysis, costume design of Korea, China, Japan had differences on form, color, texture, pattern, ornament, etc. 2) The hierarchic structure of oriental costume image consisted of elegance, sexy, feminine. Through factor analysis about oriental costume image 7 factors were identified; Attention, Attractiveness, Sexiness, Activeness, Weightness, Classics, Classics, Maturity. It was found out strongly that Korean costume image was simple and comfort image, Chinese costume image was sexy and feminine image, Japanese costume image was luxurious and mature image.

• 한국통신학회논문지
• /
• 제34권10B호
• /
• pp.1111-1116
• /
• 2009

본 논문에서는 집적 영상의 획득과 복원을 이용하여 왜곡에 강인한 물체를 인식하는 방법을 연구한다. 해당 화소들의 확률적 특성인 평균과 표준편차를 이용하여 3차원 공간에서 물체를 복원하고 거리를 추정한다. 표적인식은 Fisher 선형판별법(linear discriminant analysis, LDA)과 주성분 분석법(principal component analysis, PCA) 기술을 결합한 통계적 분류기(statistical classifier)로 수행한다. Fisher 선형판별법은 클래스 간의 판별력을 최대로 하고 주성분 분석법은 Fisher 선형판별법을 수행하기 위한 차원축소를 실행한다. 주성분 분석법은 차원축소 후 복원된 벡터와 원 벡터의 오차를 최소화하는 기술로 알려져 있다. 실험 및 시뮬레이션을 통하여 면외(out-of-plane) 회전된 표적을 본 논문에서 제안한 방법으로 분류한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.1081-1084
• /
• 2002

In this study, we perform 3-D reconstruction of human proximal femur from DICOM files by using voxel mesh algorithm. After 3-D reconstruction, the model converted to Finite Element model which developed for automatically making not only 3-D geometrical model but also FE model from medical image dataset. During this job, trabecular pattern, one of characteristic of human bone can be added to the model by means of giving it's own elastic property calculated from intensity in CT scanned image to the each voxel. And then another model is made from same image dataset which have two material properties - one corresponds to cortical bone, another to trabecular bone. Finally, validity of voxel mesh technique is verified through comparing results of FE analysis, free vibration and stress analysis.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권3호
• /
• pp.205-208
• /
• 2013

일반적으로 이진패턴 변환은 조명 변화에 강인한 특성을 가지므로, 얼굴인식 및 표정인식 분야에 널리 사용되고 있다. 이에, 본 논문에서는 기존의 LDP(Local Directional Pattern)의 텍스처 성분을 개선한 MLDP(Modified LDP) 변환 영상에 2D-PCA(Two-Dimensional Principal Component Analysis) 알고리즘을 결합한 조명변화에 강인한 얼굴인식 방법에 대하여 제안한다. 기존의 LBP(Local Binary Pattern)나 LDP와 같은 이진패턴 변환들이 히스토그램 특징 추출을 위해 주로 사용되는 것과는 다르게, 본 논문에서 제안하는 방법은 MLDP 영상을 2D-PCA 특징추출을 위해 직접 사용한다는 특성을 갖는다. 제안 방법의 성능평가는 PCA(Principal Component Analysis), 2D-PCA 및 가버변환 영상과 LBP를 결합한 알고리즘을 사용하여, 다양한 조명변화 환경에서 구축된 Yale B 및 CMU-PIE 데이터베이스를 이용하여 수행되었다. 실험 결과, MLDP 영상과 2D-PCA를 사용한 제안 방법이 가장 우수한 인식 성능을 보임을 확인하였다.

• 한국음향학회지
• /
• 제15권6호
• /
• pp.90-98
• /
• 1996

본 논문에서는 한글의 형태소 분석에 기초한 청각장애자용 수화영상 변환시스템을 제안하였다. 제안된 시스템은 입력 문자열에 대해 형태소 분석에 의한 음운성분과 접속정보를 추출한 다음, 이에 대응한 수화영상을 구축된 수화영상 데이터베이스를 통하여 정확히 출력한다. 효과적인 수화영상변환을 위해 입력문자열에 대한 형태소 분석부와 수화패턴 참조를 위한 수화언어기술부로 이루어진 언어정보기술사전을 구성하였다. 수화패턴은 중복을 피하기 위해 기본수화, 복합수화 그리고 유사수화단어로 분류하여 작성하였으며, 실험을 통해 제안된 시스템의 유용성을 확인하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.509-511
• /
• 2004

This paper outlines the development of image processing system, which will allow the general users in Government and Public organizations easily to use and apply KOMPSAT EOC images in their own business. The system includes an import/export module of EOC image distributed in Hierarchical Data Format (HDF) file and various image processing analysis modules. Especially, the image mosaic and subset functions are designed to use EOC image as an image map, generating the Ortho-image module. To update the various spatial data with EOC image, some essential modules such as change detection by pattern recognition, overlay between images and vector data, and modification of vector data are implemented in the system. The system is developed based on the user request analysis of government agency, and suited for more efficient use of satellite image in public applications. Such system is expected to contribute to practical application of KOMPSAT-2 that will be launched in 2005. Further efforts will be made to accommodate the KOMPSAT -2 MSC data.

• 한국지역사회생활과학회지
• /
• 제17권2호
• /
• pp.89-103
• /
• 2006

This study was performed to provide sources of nutrition education for female adolescents by identifying eating disorder patterns and their relationships with self-body image, weight control, and eating behavior. A total of 329 female middle school students were recruited and completed a general characteristics survey, the Eating Attitudes Test(EAT-26), a perception of self-body image survey, a concern for weight control survey, an eating behavior survey, and the Mini Dietary Assessment Index(MDA). Eating disorder patterns were identified to be obesity stress and weight control(OW), risk of binge eating(RB), and dietary restraint(DR) by factor analysis. OW pattern was related with stout body shape, body dissatisfaction, experience of weight control, skipping of dinner, and low MDA score. RB pattern was associated with lean body shape, body satisfaction, indiscreet snack behavior, and the eating time of snacks. The DR pattern was associated with normal body shape, regular meal times, desirable snack behavior, and high MDA scores. The results indicated that the eating patterns of adolescent were not identical to existing diagnostic categories. Furthermore, each eating pattern displayed different characteristics of perception on self-body image, concern for weight control, and eating behavior. In conclusion, nutrition education for female middle school students could reflect the different characteristics of each eating disorder pattern.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.589-592
• /
• 1999

Matching is a key problem in computer vision, image analysis and pattern recognition. In this paper a multiscale image matching algorithm by wavelet local extrema is proposed. This algorithm is based on the multiscale wavelet transform of the curvature which can utilize both the information of local extrema positions and magnitudes of transform results. This method has advantages in computational cost to a single scale image matching. It is also rotation-, translation-, and scale-independent image matching method. This matching can be used for the recognition of occluded objects.

• 디지털산업정보학회논문지
• /
• 제8권2호
• /
• pp.31-40
• /
• 2012

Face recognition refers to the process of identifying individuals based on their facial features. It has recently become one of the most popular research areas in the fields of computer vision, machine learning, and pattern recognition because it spans numerous consumer applications, such as access control, surveillance, security, credit-card verification, and criminal identification. However, illumination variation on face generally cause performance degradation of face recognition systems under practical environments. Thus, this paper proposes an novel face recognition system using a fusion approach based on local binary pattern and two-dimensional principal component analysis. To minimize illumination effects, the face image undergoes the local binary pattern operation, and the resultant image are divided into two sub-images. Then, two-dimensional principal component analysis algorithm is separately applied to each sub-images. The individual scores obtained from two sub-images are integrated using a weighted-summation rule, and the fused-score is utilized to classify the unknown user. The performance evaluation of the proposed system was performed using the Yale B database and CMU-PIE database, and the proposed method shows the better recognition results in comparison with existing face recognition techniques.

• 전기학회논문지
• /
• 제63권6호
• /
• pp.797-803
• /
• 2014

In this paper, 3D face recognition system is designed by using polynomial based on RBFNNs. In case of 2D face recognition, the recognition performance reduced by the external environmental factors such as illumination and facial pose. In order to compensate for these shortcomings of 2D face recognition, 3D face recognition. In the preprocessing part, according to the change of each position angle the obtained 3D face image shapes are changed into front image shapes through pose compensation. the depth data of face image shape by using Multiple Point Signature is extracted. Overall face depth information is obtained by using two or more reference points. The direct use of the extracted data an high-dimensional data leads to the deterioration of learning speed as well as recognition performance. We exploit principle component analysis(PCA) algorithm to conduct the dimension reduction of high-dimensional data. Parameter optimization is carried out with the aid of PSO for effective training and recognition. The proposed pattern classifier is experimented with and evaluated by using dataset obtained in IC & CI Lab.