• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.107-115
• /
• 2009

Skin color detection is used to classify input pixels into skin and non skin area, and it requires the classifier to have a high classification rate. In previous work, most classifiers used single color model for skin color detection. However the classification rate can be increased by using more than one color model due to the various characteristics of skin color distribution in different color models, and the MLP is also invested as a more efficient classifier with less parameters than other classifiers. But the input dimension and required parameters of MLP will be increased when using two color models in skin color detection, as a result, the increased parameters will cause the huge teaming time in MLP. In this paper, we propose a MLP based classifier with less parameters in two color models. The proposed partially connected MLP based on two color models can reduce the number of weights and improve the classification rate. Because the characteristic of different color model can be learned in different partial networks. As the experimental results, we obtained 91.8% classification rate when testing various images in RGB and CbCr models.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.131-143
• /
• 2004

Given a path represented by a sequence of link numbers in a graph, the vine is differentiated from the loop in a sense that any link number can be visited in the path no more than once, while more than once in the loop. The vine provides a proper idea on complicated travel patterns such as U-turn and P-turn witnessed near intersections in urban transportation networks. Application of the link label method(LLM) to the shortest Path algorithms(SPA) enables to take into account these vine travel features. This study aims at expanding the LLM to a K-th path search algorithm (KPSA), which adopts the node-based-label correcting method to find a group of K number of paths. The paths including the vine type of travels are conceptualized as drivers reasonable route choice behaviors(RRCB) based on non-repetition of the same link in the paths, and the link-label-based MPSA is proposed on the basis of the RRCB. The small-scaled network test shows that the algorithm sequence works correctly producing multiple paths satisfying the RRCB. The large-scaled network study detects the solution degeneration (SD) problem in case the number of paths (K) is not sufficient enough, and the (K-1) dimension algorithm is developed to prevent the SD from the 1st path of each link, so that it may be applied as reasonable alternative route information tool, an important requirement of which is if it can generate small number of distinct alternative paths.

• Archives of design research
• /
• v.19 no.5 s.67
• /
• pp.233-242
• /
• 2006

The purpose of this study is to investigate communication efficacy of advertisement text through audience responses. This study approached qualitatively to KT&G TV commercials. The research proceeded as follows: First, as background theory, studies on audience focusing advertisement criticism and the interpretation of advertising texts were reviewed. Secondly, the characteristics of the audiences of the advertisements, analyzed through in-depth individual interviews as well as group interviews, were incorporated into a broad theme and then divided into different dimensions. Finally, the audiences' decoding code and critic reponses in reading ambiguous advertising texts, and the interrelationship between strategic ambiguity were discussed under a unified model. The major findings of this study are as follows: In interpreting the ambiguous advertising texts, the audiences use various decoding codes such as language, visuals, technology and rhetoric, and various critic responses such as linguistic, macroscopic, schematic, non-verbal and socio-cultural factors, in quite comprehensive manner. Also, it was shown that audiences make use of different decoding strategies in terms of their recognition, reliability, emotional attitude, and behavior. It can therefore be concluded that the strategic ambiguity has its limit in explaining its effectiveness in the entire dimensions of recognition, emotional attitude, and behavior, in the sense that the strategic ambiguity is most effective in recognition while it invokes more negativity in the behavioral dimension. Finally, this empirical study, focusing on qualitative analyses, may have its limit as well; however, deeper statistic-qualitative studies in the future could compensate for it.

• The Journal of Engineering Geology
• /
• v.20 no.2
• /
• pp.183-189
• /
• 2010

Fault gouge samples were collected from the fault cores of the boundary faults between the Cretaceous Basement and the Tertiary Waeup Basin. Fractal dimensions (D) were obtained by using survivor grains which were analysed from six thin sections of the gouges under the optical microscope. The elliptical survivor grains show a shape preferred orientation almost parallel to clay foliation in matrix, suggesting that it was formed by the rotation of the survivor grains in abundant fine-grained matrix during repeated fault slips. The size distributions of the survivor grains follow power-laws with fractal dimensions in the 2.40-3.02 range. D values of all samples but one are higher than a specific D value equal to 2.58 which predicts the self similarity of fragmentation process in constrained comminution model (Sammis et al., 1987), which indicates large fault slip and multiple faulting. Probably the higher D values than 2.58 mean the non-self-similar evolution of cataclastic rocks where fragmentation mechanism changed from constrained comminution to the grain abrasion accompanying selective fracture of larger grains.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.158-168
• /
• 2018

The purpose of this study was to investigate the effect of applying physical expression program through dancing on the post-traumatic growth of domestic violence female victims. The subjects of this study were female victims of domestic violence living in shelters (7 facilities) for women victims of domestic violence in Seoul, consisting of 23 experimental groups and 23 control groups. The dancing healing physical expression program applied to the experimental group consisted of 18 sessions, which was conducted three times a week for 6 weeks, and each session was conducted for 90 minutes. This study was aimed to dancing based on physical expression and movement experience, but focuses on improvisational, non-formal and creative expression for inner expression. We referred to the activities and principles of previous studies, and applied characters, which were counseling techniques, interactions, and healing principles of previous counseling psychology studies on domestic violence and trauma, to every stage of the session. As a result of this study, it was found that the dancing healing physical expression program had an effect on the entire post-traumatic growth of the experimental group and lower dimension lists of the depth of interpersonal relationship, self-perception, potential discovery, spiritual interest level, The results of the post - test were compared. There was a significant difference between the experimental and control groups after the test. In conclusion, this study aimed to understand the fundamental and healing attributes of dance, and provided basic data to establish a virtuous intervention strategy that provided opportunities for self-recovery to those who experienced psychological pain, such as women victimized by domestic violence at the social aspect.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• The Journal of Korean Academy of Prosthodontics
• /
• v.55 no.4
• /
• pp.410-418
• /
• 2017

Amelogenesis imperfecta characterized as abnormally formed enamel is caused by a defect of unique group of genes. Patients affected by this disease might have difficulties in social and psychological aspects due to non-esthetic teeth as well as functional problems caused by enamel detachment and tooth wear from their early ages. Adult patients with amelogenesis imperfecta can be treated with full-mouth restorations, which make functional and esthetic rehabilitations of severely worn tooth. However, the anterior open bite and lack of occlusal clearance for posterior teeth restorations due to compensatory extrusion are the intervening factors in the prosthetic treatment. Therefore, the determination of anterior tooth lengths, vertical dimension, and anterior guidance should be set carefully. Recently, computer-aided design and computer-aided manufacturing (CAD/CAM) techniques help systematic approaches and enable dentists to reduce time-consuming procedures in the diagnosis and treatment of full-mouth rehabilitation. This case report demonstrates the successful full mouth rehabilitation using a CAD/CAM system in a young adult patient with amelogenesis imperfecta and anterior open bite.

• Journal of Environmental Science International
• /
• v.27 no.5
• /
• pp.291-297
• /
• 2018

Vertical farming systems offer many advantages in urban spaces. They have also been proposed as an engineering solution to increase the productivity per unit area of cultivated land by extending crop production in the vertical dimension. However, soil water retention is a major constraint affecting the plant environment. This study analyzed the effects of growth environment of Tropaeolum majus and Fragaria spp., on the vertical farming system, by using four different types of cover material types including sphagnum moss (Control), a shading net (S.N.), multi-layered fabric (M.L.F.), and non-woven fabric (N.W.F.). The volumetric soil moisture contents and plant characteristics were investigated from May to September 2014. Plant materials were individually cultivated in hanging baskets measuring $30{\times}17{\times}17cm$, filled with a mixture of soil and perlite, and placed at 1.5m height. Each treatment was performed in quadruplicate and consisted of five plants, amounting to a total of 20 plants. The analysis indicated that different covers were associated with multiple functions and soil water retention improvements may have a positive impact on the vertical farming system. The difference in soil water retention increased in the following order: M.L.F. > Control > N.W.F. > S.N.. Furthermore, the differences in plant height and survival rate increased in the following order: M.L.F. > Control > N.W.F. > S.N. Therefore, M.L.F yielded satisfactory good response for the vertical farming system of cover materials. Our results clearly demonstrate that vertical spaces represent an attractive alternative to urban farming and suggest that further increases in yield may be achieved via different cover materials in vertical farming using hanging baskets.

• Journal of the Korean Geophysical Society
• /
• v.3 no.3
• /
• pp.161-174
• /
• 2000

Bayesian inversion is a stable approach to infer the subsurface structure with the limited data from geophysical explorations. In geophysical inverse process, due to the finite and discrete characteristics of field data and modeling process, some uncertainties are inherent and therefore probabilistic approach to the geophysical inversion is required. Bayesian framework provides theoretical base for the confidency and uncertainty analysis for the inference. However, most of the Bayesian inversion require the integration process of high dimension, so massive calculations like a Monte Carlo integration is demanded to solve it. This method, though, seemed suitable to apply to the geophysical problems which have the characteristics of highly non-linearity, we are faced to meet the promptness and convenience in field process. In this study, by the Gaussian approximation for the observed data and a priori information, fast Bayesian inversion scheme is developed and applied to the model problem with electric well logging and dipole-dipole resistivity data. Each covariance matrices are induced by geostatistical method and optimization technique resulted in maximum a posteriori information. Especially a priori information is evaluated by the cross-validation technique. And the uncertainty analysis was performed to interpret the resistivity structure by simulation of a posteriori covariance matrix.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.651-676
• /
• 2017

Shadow images are a representative medium and means of expression for the imagination that exists between consciousness and unconsciousness for thousands of years. Wherever light exists, people create play with their own shadows without special skills, and have made a fantasy at once. Shadow images have long been used as subjects and materials of literacy, art, philosophy, and popular culture. Especially in the field of art, people have been experimenting with visual stimulation through the uniqueness of simple silhouettes images. In the field of animation, it became to be recognized as a form of non - mainstream areas that are difficult to make. However, shadow images have been used more actively in the field of digital arts and media art. In this Environment with technologies, Various formative imaginations are being expressed more with shadow images in a new dimension. This study is to introduce and analyze these trends, the aesthetic transformations and extended methods focusing on digital silhouette animation and recent media art works using shadow images. Screen-based silhouette animation combines digital technology and new approaches that have escaped conventional methods have removed most of the elements that have been considered limitations, and these factors have become a matter of choice for the directors. Especially, in the display environment using various light sources, projection, and camera technology, shadow images were expressed with multiple-layered virtual spaces, and it becomes possible to imagine a new extended imagination. Through the computer vision, it became possible to find new gaze and spatial images and use it more flexibly. These changes have given new possibility to the use shadow images in a different way.