• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.731-736
• /
• 2008

In this paper, we propose the movement detection algorithm by using virtual skeleton model. To do this, first, we eliminate error values by using conventioanl method based on RGB color model and eliminate unnecessary values by using the HSI color model. Second, we construct the virtual skeleton model with skeleton information of 10 peoples. After matching this virtual model to original image, we extract the real head silhouette by using the proposed circle searching method. Third, we extract the object by using the mean-shift algorithm and this head information. Finally, we validate the applicability of the proposed method through the various experiments in a complex environments.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1616-1623
• /
• 1996

In general, in order to recognize and modelling the 3-D object, it is necessary to have the method to express the shape of 3-D object. In case of 2-D like silhouette image, the extraction of vertex on the boundary of the object can be obtained by using the 2-D curvature function. But, in case of 3-D curvature function that can calculate the surface curvature values of 3-d object doesn't exist, it is difficult to express the share of 3-D object. Therefore, in this paper, a new method is presented. With this presented method, the approximated surface curvature values and vertex of 3-D object can be obtained effectively using the principle of 2-D curvature and the least square method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.422-428
• /
• 2008

In this paper, we propose the robust object detection algorithm with spatial gradient information. To do this, first, we eliminate error values that appear due to complex environment and various illumination change by using prior methods based on hue and intensity from the input video and background. Visible shadows are eliminated from the foreground by using an RGB color model and a qualified RGB color model. And unnecessary values are eliminated by using the HSI color model. The background is removed completely from the foreground leaving a silhouette to be restored using spatial gradient and HSI color model. Finally, we validate the applicability of the proposed method using various indoor and outdoor conditions in a complex environments.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.85-93
• /
• 2019

The purpose of this study is to provide basic data for the development of clothing which can improve the satisfaction of male university students' body shape by classifying the perception of body shape and examining characteristics by type. The types of recognition of body shape of male college students were classified into five types: developed upper body with protruding under abdomen, normal body with long legs, developed under body with big skeleton, skinny body, and ladder type normal body. The actual body shape was classified into three. The Y type had a long chest length and a shoulder developed, and the lower body silhouette was plain and short. Type H was flat with little protrusion from the chest to the hip. Type X has a larger hip and longer hip length than the waist. Body type was classified based on bust, waist, and hip circumference, but recognition body type was classified based on visual characteristics. It is thought that ergonomic consideration is needed to cover the disadvantages of each body type considering the aesthetic part as well as wearing comfort in accordance with the trend of the fashion market nowadays that the slim fit is generalized. This study was limited to male university students in their early 20s in Chungbuk province. Therefore, we could not grasp attitudes and perceptions of male university students living in other provinces. Therefore, we should pay attention to the generalization of the results of this study.

• Journal of Fashion Business
• /
• v.26 no.4
• /
• pp.1-17
• /
• 2022

In the fashion industry, the demand for new perspectives to express creativity has always been high. Expression of new perspectives allows creative ideas to emerge, thereby breaking away from habitual and familiar perceptions. The purpose of this study is to identify and analyze how the theory of defamiliarization is being applied in fashion design by the brand Münn, which claims defamiliarization as a design philosophy. The study examined the concepts and the characteristics of Viktor Shklovsky by literature review and derived the main characteristics of the defamiliarization theory for fashion design analysis based on studies that used defamiliarization in other fields. Furthermore, after analyzing Münn's collection, we found how the main characteristics of defamiliarization derived from reviews were expressed in Münn's designs. The defamiliarization in Münn's collection was first, 'breakaway from stereotype' appeared through re-recognition of perception and unexpected use of heterogeneous materials. Second, 'distortion and analogy through image' was revealed through the East and West clothing-making methods, which broke away from the stereotype of image and the juxtaposition and cultural reconstruction of details. Third, 'transition of viewpoint' was shown as an avant-garde sense through the conversion of usage purpose of design, material, or items in which subjects and objects were converted with conceptual design and material or silhouette.

• Journal of Korea Multimedia Society
• /
• v.10 no.8
• /
• pp.981-996
• /
• 2007

In this paper, we describe a method that can recognize gestures by obtaining motion features information with principal factor analysis from sequential gesture images. In the algorithm, firstly, a two dimensional silhouette region including human gesture is segmented and then geometric features are extracted from it. Here, global features information which is selected as some meaningful key feature effectively expressing gestures with principal factor analysis is used. Obtained motion history information representing time variation of gestures from extracted feature construct one gesture subspace. Finally, projected model feature value into the gesture space is transformed as specific state symbols by grouping algorithm to be use as input symbols of HMM and input gesture is recognized as one of the model gesture with high probability. Proposed method has achieved higher recognition rate than others using only shape information of human body as in an appearance-based method or extracting features intuitively from complicated gestures, because this algorithm constructs gesture models with feature factors that have high contribution rate using principal factor analysis.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.15-37
• /
• 2004

With the growth in the size of datasets, data mining has recently become an important research topic. Especially, interests about spatio-temporal data mining has been increased which is a method for analyzing massive spatio-temporal data collected from a wide variety of applications like GPS data, trajectory data of surveillance system and earth geographic data. In the former approaches, conventional clustering algorithms are applied as spatio-temporal data mining techniques without any modification. In this paper, we focused to SOM that is the most common clustering algorithm applied to clustering analysis in data mining wet and develop the spatio-temporal data mining module based on it. In addition, we analyzed the clustering results of developed SOM module and compare them with those of K-means and Agglomerative Hierarchical algorithm in the aspects of homogeneity, separation, separation, silhouette width and accuracy. We also developed specialized visualization module fur more accurate interpretation of mining result.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.53-58
• /
• 2024

Traffic accidents are not only a threat to human lives but also pose significant societal costs. Recently, research has been conducted to address the issue of traffic accidents by predicting the risk using deep learning technology and spatiotemporal information of roads. However, while traffic accidents are influenced not only by the spatiotemporal information of roads but also by human factors, research on the latter has been relatively less active. This paper analyzes driver groups and characteristics by applying clustering techniques to a traffic accident dataset and proposes and applies a method to calculate the Risk Level for each driver group and characteristic. In this process, the preprocessing technique suggested in this paper demonstrates a higher Silhouette Score of 0.255 compared to the commonly used One-Hot Embedding & Min-Max Scaling techniques, indicating its suitability as a preprocessing method.

• Korean Journal of Human Ecology
• /
• v.22 no.5
• /
• pp.461-476
• /
• 2013

This study aims to provide practical information of both color and hands of cotton fabrics dyed with persimmon dye powder for natural dyeing fashion industries by investigating dyeing behavior and color gamut, by testing mechanical properties depending on color characteristics, and finally by evaluating dyeing fastness. As results, the persimmon dye powder obtained by extracting the fruits to final solid powder was found as containing tannin and it partially coated between and on fibers similarly to traditionally dyed one. The K/S values of non-mordanted fabric and two differently mordanted ones with Fe and Cu seemed to reach their equilibrium from 800, 800, and 600% (owf), respectively. Yellow-red was the only one hue shown while tones were various as pale (p), light grayish (ltg), soft (sf), dull (d), grayish (g), and dark grayish (dkg). In mechanical properties, the dyed fabrics with p and ltg tended to be less altered than undyed ones whereas d and d kg by higher bath concentrations could be applied to boxy silhouette owing to their increased stiffness and less stretchability. Although fastness to dry cleaning and stain was good, color change by washing and rubbing needed to be improved.

• Journal of Internet Computing and Services
• /
• v.9 no.3
• /
• pp.91-101
• /
• 2008

This paper proposes component-based density propagation for tracking a component-based human body model that comprises components and their flexible links. We divide a human body into six body parts as components - head, body, left arm, right arm, left foot, and right foot - that are most necessary in tracking its movement. Instead of tracking a whole body's silhouette, using component-based density propagation, the proposed method individually tracks each component of various parts of human body through a human body model connecting the components. The proposed human body tracking system has been applied to track movements usee for young children's movement education: balancing, hopping, jumping, walking, turning, bending, and stretching. This proposed system demonstrated the validity and effectiveness of movement tracking by independently detecting each component in the human body model and by acquiring an average 97% of high tracking rate.