• 제어로봇시스템학회논문지
• /
• 제16권10호
• /
• pp.957-962
• /
• 2010

If we want to recognize the human's emotion via the facial image, first of all, we need to extract the emotional features from the facial image by using a feature extraction algorithm. And we need to classify the emotional status by using pattern classification method. The AAM (Active Appearance Model) is a well-known method that can represent a non-rigid object, such as face, facial expression. The Bayesian Network is a probability based classifier that can represent the probabilistic relationships between a set of facial features. In this paper, our approach to facial feature extraction lies in the proposed feature extraction method based on combining AAM with FACS (Facial Action Coding System) for automatically modeling and extracting the facial emotional features. To recognize the facial emotion, we use the DBNs (Dynamic Bayesian Networks) for modeling and understanding the temporal phases of facial expressions in image sequences. The result of emotion recognition can be used to rehabilitate based on biofeedback for emotional disabled.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.871-891
• /
• 2019

Visual tracking is a challenging task that needs learning an effective model to handle the changes of target appearance caused by factors such as pose variation, illumination change, occlusion and motion blur. In this paper, a novel tracking algorithm based on weighted local sub-space reconstruction error is presented. First, accounting for the appearance changes in the tracking process, a generative weight calculation method based on structural reconstruction error is proposed. Furthermore, a template update scheme of occlusion-aware is introduced, in which we reconstruct a new template instead of simply exploiting the best observation for template update. The effectiveness and feasibility of the proposed algorithm are verified by comparing it with some state-of-the-art algorithms quantitatively and qualitatively.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2007년도 학술대회 1부
• /
• pp.630-635
• /
• 2007

In this paper, we propose a system for multiple people tracking using fragment based histogram matching. Appearance model is based on IHLS color histogram which can be calculated efficiently using integral histogram representation. Since histograms will loss all spatial information, we define a fragment based region representation which retain spatial information, robust against occlusion and scale issue by using disparity information. Multiple people labeling is maintained by creating online appearance representation for each people detected in scene and calculating fragment vote map. Initialization is performed automatically from background segmentation step.

• ETRI Journal
• /
• 제34권3호
• /
• pp.399-409
• /
• 2012

In this paper, we propose a new color histogram model for object tracking. The proposed model incorporates the color arrangement of the target that encodes the relative spatial distribution of the colors inside the object. Using the color arrangement, we can determine which color bin is more reliable for tracking. Based on the proposed color histogram model, we derive a mean shift framework using a modified Bhattacharyya distance. In addition, we present a method of updating an object scale and a target model to cope with changes in the target appearance. Unlike conventional mean shift based methods, our algorithm produces satisfactory results even when the object being tracked shares similar colors with the background.

• 한국컴퓨터정보학회논문지
• /
• 제19권1호
• /
• pp.203-213
• /
• 2014

본 논문에서는 곤충 종의 외관구조인 머리, 몸통, 날개, 다리에 대한 관찰자의 일반적이고 수평적인 관찰특성에 따라 자유롭게 곤충 종을 관찰함으로써 관찰 곤충 검색엔진에서의 사용자 만족도 제고와 보다 효율적인 관찰학습의 방법을 제안한다. 자연생태 환경에서 초보 학습자의 효율적인 관찰검색과 효과적 학습을 위해서는 생물학적 분류체계가 아닌 곤충 종의 외관구조 즉, 외부 신체구조의 모양과 특성 중심의 곤충관찰 기반의 검색(Insect Search by Observation based on Insect Appearance: ISOIA)이 필요하다. 그러므로 본 연구에서는 곤충의 외관구조인 머리, 몸통, 날개, 다리에 대한 관찰자의 일반적인 관찰방법에 따른ISOIA 검색방식을 제안하고, 기존의 ISBC와 ISOBC 검색체계에 대한 사용 만족도를 비교 분석하여 본 논문에서 제안하는 ISOIA 검색 방안이 우수함을 보이고자 한다.

• 제어로봇시스템학회논문지
• /
• 제17권2호
• /
• pp.93-101
• /
• 2011

For mobile robot, recognizing its current location is very important to navigate autonomously. Especially, loop closing detection that robot recognize location where it has visited before is a kernel problem to solve localization. A considerable amount of research has been conducted on loop closing detection and localization based on appearance because vision sensor has an advantage in terms of costs and various approaching methods to solve this problem. In case of scenes that consist of repeated structures like in corridors, perceptual aliasing in which, the two different locations are recognized as the same, occurs frequently. In this paper, we propose an improved method to recognize location in the scenes which have similar structures. We extracted salient regions from images using visual attention model and calculated weights using distinctive features in the salient region. It makes possible to emphasize unique features in the scene to classify similar-looking locations. In the results of corridor recognition experiments, proposed method showed improved recognition performance. It shows 78.2% in the accuracy of single floor corridor recognition and 71.5% for multi floor corridors recognition.

• 한국의류산업학회지
• /
• 제17권5호
• /
• pp.718-730
• /
• 2015

This study investigated the correlation between the level of consistency in fashion show models' appearance and design concept through a statistical and qualitative analysis of the S/S Paris Collection 2014. The following conclusions have been drawn in this study. First, the percentage of models of color was very low in regards to the physical appearance of models; in addition, there was a higher percentage of Caucasian models for collections with a high level of consistency in models' physical appearance. Collections with a high percentage of models of color indicate more casual design concepts and the promotion of diversity in racial background is considered more effective for street fashion. Second, collections with a high level of consistency in models' physical appearance tend to control various elements that constitute a physical appearance through more detailed planning and stage direction. Third, there is a tendency to reinforce design concepts by creating a consistency in the overall physical appearance of models. This affirms that their physical appearance is determined by brand (i.e. designer) and is used to maximize a design concept delivery. The results of this study suggests that the physical appearance of models must be determined in line with the design concept versus detailed planning that must consider audience perspectives as well as adjust the show's length and the interval between each model appearing on the stage.

• 디지털융복합연구
• /
• 제12권7호
• /
• pp.239-245
• /
• 2014

본 논문에서는 얼굴의 전체적인 특징(윤곽선, 얼굴크기, 눈, 코) 분석에 기반을 둔 가중치 주름 검출 방법을 제안한다. 첫째 입력된 영상에서 능동적 외향 방법을 이용하여 얼굴의 전체적인 주요 성분을 검출하게 되는데, 크게 형태 기반과 외향 방법으로 구성되어 있다. 이것은 얼굴 모델을 학습하고, 학습된 모델을 기반으로 새로운 영상에서 얼굴을 정합할 때 사용된다. 두 번째로는 영상에서 얼굴과 배경을 분리하고, 얼굴에서 주름 확률이 가장 큰 곳 네 곳을 선정하여 주름 가중치를 높게 부과하다. 마지막으로 가중치를 부여한 관심 영역에 대해서 캐니에지 알고리즘을 적용하여 주름을 검출하게 된다. 제안한 알고리즘은 다양한 종류의 영상을 사용하여 실험 하였으며, 실험결과 대부분의 영상에서 높은 성능의 얼굴 및 주름 검출 결과를 보였다.

• 한국의류학회지
• /
• 제25권7호
• /
• pp.1227-1238
• /
• 2001

This study was based on social comparison theory, and the covariance structure model was designed, connecting sociocultural attitude, multifaceted body image, and clothing behaviour under sociocultural influence. The practical purpose of this study is to identify the effect of sociocultural attitude toward physical appearance on the affective aspect of body images, the cognitive/behavioral aspect of body images and clothing benefits sought, and to examine the age difference in the female adolescents. The results of this were as follows: 1) Sociocultural attitude toward physical appearance had a negative effect directly on the affective aspect of body images, and showed the highest value in the group of high school girls 2) Sociocultural attitude toward physical appearance had a positive influence directly on the cognitive/behavioral aspect of body images, and high school girls'model showed the highest values significantly as well 3) High school girls'model showed the highest value significantly in the effect of the affective aspect of body images on the cognitive/behavioral aspect of body images. However, college group's model didn's show significant value 4) Middle school girls'model showed higher value positively than the other groups in the effect of the cognitive/behavioral aspect of body images on clothing benefits sought, and the high school girls' model showed higher value negatively in the effect of the affective aspect of body images on clothing benefits sought.

• 한국정보통신학회논문지
• /
• 제8권2호
• /
• pp.456-463
• /
• 2004

본 논문에서는 다양한 조명하에서 실시간으로 눈을 검출하고 추적하는 새로운 방법을 제안하고자 한다. 기존의 능동적 적외선을 이용한 눈 검출 및 추적 방법은 외부의 조명에 매우 민감하게 반응하는 문제점을 가지고 있으므로, 본 논문에서는 적외선 조명을 이용한 밝은 동공 효과와 전형적인 외형을 기반으로 한 사물 인식 기술을 결합하여 외부 조명의 간섭으로 밝은 동공 효과가 나타나지 않는 경우에도 견실하게 눈을 검출하고 추적 할 수 있는 방법을 제안한다. 눈 검출과 추적을 위해 SVM과 평균 이동 추적방법을 사용하였고, 적외선 조명과 카메라를 포함한 영상 획득 장치를 구성하여 제안된 방법이 효율적으로 다양한 조명하에서 눈 검출과 추적을 할 수 있음을 보여 주었다.