• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.396-404
• /
• 2014

The field of searching clothing, which is very difficult due to the nature of the informal sector, has been in an effort to reduce the recognition error and computational complexity. However, there is no concrete examples of the whole progress of learning and recognizing for cloth, and the related technologies are still showing many limitations. In this paper, the whole process including identifying both the person and cloth in an image and analyzing both its color and texture pattern is specifically shown for classification. Especially, deformable search descriptor, LBPROT_35 is proposed for identifying the pattern of clothing. The proposed method is scale and rotation invariant, so we can obtain even higher detection rate even though the scale and angle of the image changes. In addition, the color classifier with the color space quantization is proposed not to loose color similarity. In simulation, we build database by training a total of 810 images from the clothing images on the internet, and test some of them. As a result, the proposed method shows a good performance as it has 94.4% matching rate while the former Dense-SIFT method has 63.9%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.21-29
• /
• 2011

At existing skin detection methods using skin color information defined based on the prior knowldege, threshold value to be used at the stage of dividing the backround and the skin region was decided on a subjective point of view through experiments. Also, threshold value was selected in a passive manner according to their background and illumination environments in these existing methods. These existing methods displayed a drawback in that their performance was fully influenced by the threshold value estimated through repetitive experiments. To overcome the drawback of existing methods, this paper propose a skin region detection method using a histogram approximation based on the mean shift algorithm. The proposed method is to divide the background region and the skin region by using the mean shift method at the histogram of the skin-map of the input image generated by the comparison of the similarity with the standard skin color at the CbCr color space and actively finding the maximum value converged by brightness level. Since the histogram has a form of discontinuous function accumulated according to the brightness value of the pixel, it gets approximated as a Gaussian Mixture Model (GMM) using the Bezier Curve method. Thus, the proposed method detects the skin region by using the mean shift method and actively finding the maximum value which eventually becomes the dividing point, not by using the manually selected threshold value unlike other existing methods. This method detects the skin region high performance effectively through experiments.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.37 no.1
• /
• pp.23-36
• /
• 2011

The purpose of this study is to make theoretical examinations into the makeup trend shown in digital communication environment and thereby determine potential associations of makeup trend with digital communication environment and characterize said trend, so that it can provide reference materials required for follow-up studies. This study comes to the following findings: First, it is found that there are sociocultural characteristics of digital communication environment, such as interactivity, technology-orientedness, sentiment-orientedness and mixture of time and space. Secondly, it is found that trends developed in makeup fall categorically into interactivity, virtuality, amusement and mobility. Thirdly, it is found that each type of digital communication adopts a mixture and juxtaposition of contemporary styles or categories with traditional ones through eclectic combination based on open-minded and horizontal ideas. Fourthly, it is found that a trend from digital communication environment doesn't coincide perfectly with any makeup trend, but the former trend works interactively and organically with the latter trend on the basis of homogeneity and similarity within a general framework that represents external esthetics of human being. With the creation of digital communication environment, our contemporary society forms as the complex phenomena of digital society in a combination and destruction of different categories beyond any certain international boundary, so that a hybrid tendency appears in contemporary makeup trend as well. Based on these findings, this study has its implications in the sense that it gives a new viewpoint based on design, formative characteristics and expression styles of makeup, and also provides useful reference materials for related industrial sectors.

• Tunnel and Underground Space
• /
• v.27 no.1
• /
• pp.50-57
• /
• 2017

In this study, the experiment for determining shock loss at the branch is conducted for the design of network double-deck road tunnel ventilation. The shock loss coefficient that determines the quantity of shock loss has been considered only regarding the constant aspect ratio of circular or rectangular section. However the suggestion of shock loss coefficient is needed since the aspect ratio of double-deck road tunnel for small vehicle is considered around 1:3 with the low height in Korea. The experiment model was made with the scale of around 1:23 applying Reynolds similarity law, so that the shock loss coefficient on the branch of the large aspect ratio was measured. The result of the study showed that shock loss coefficients of both split branch and straight branch were measured two to three times higher than those calculated from the theoretical equation or design values of previous studies. Therefore the study resulted the effect of large aspect ratio on shock loss coefficient was huge, and it is expected that precise design value can be suggested for the design of network double-deck tunnel ventilation.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.710-721
• /
• 2010

Recently, for the advancement of embedded technology about mobile device, a new kind of service, mash-up is appeared. It is service or application combining multimedia content making tool or device and web-GIS(geographic information system) service in the mobile environment. This service can be ease to use for casual user and can apply in various ways. So, It is served in web 2.0 environment actively. But, in the mashup service, because generated multimedia contents linked with web map are new type of multimedia contents which include user's migration routes in the space such as GPS coordinates. Thus, there are no protection ways for intellectual property created by GIS web-map service users and user's privacy. In this paper, we proposed a location and user information hiding scheme for GIS web-map service. This scheme embeds location and user information into a picture that is taken by camera module on the mobile phone. It is not only protecting way for user's privacy but is also tracing way against illegal photographer who is peeping person through hidden camera. And than, we also realized proposed scheme on the mobile smart phone. For minimizing margin of error about location coordinate value against contents manipulating attacks, GPS information is embedded into chrominance signal of contents considering weight of each digit about binary type of GPS coordinate value. And for tracing illegal photographer, user information such as serial number of mobile phone, phone number and photographing date is embedded into frequency spectrum of contents luminance signal. In the experimental results, we confirmed that the error of extracted information against various image processing attacks is within reliable tolerance. And after file format translation attack, we extracted embedded information from the attacked contents without no damage. Using similarity between extracted one and original templete, we also extracted whole information from damaged chrominance signal of contents by various image processing attacks.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.2
• /
• pp.125-134
• /
• 2012

In this paper, we propose a method to analyze M:N corresponding relations in semantic matching, especially focusing on feature class matching. Similarities between any class pairs are measured by spatial objects which coexist in the class pairs, and corresponding classes are obtained by clustering with these pairwise similarities. We applied a graph embedding method, which constructs a global configuration of each class in a low-dimensional Euclidean space while preserving the above pairwise similarities, so that the distances between the embedded classes are proportional to the overall degree of similarity on the edge paths in the graph. Thus, the clustering problem could be solved by employing a general clustering algorithm with the embedded coordinates. We applied the proposed method to polygon object layers in a topographic map and land parcel categories in a cadastral map of Suwon area and evaluated the results. F-measures of the detected class pairs were analyzed to validate the results. And some class pairs which would not detected by analysis on nominal class names were detected by the proposed method.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.595-604
• /
• 2004

Automatic analysis of concepts or semantic relations from text documents enables not only an efficient acquisition of relevant information, but also a comparison of documents in the concept level. We present a multiple cause model-based approach to text analysis, where latent topics are automatically extracted from document sets and similarity between documents is measured by semantic kernels constructed from the extracted topics. In our approach, a document is assumed to be generated by various combinations of underlying topics. A topic is defined by a set of words that are related to the same topic or cooccur frequently within a document. In a network representing a multiple-cause model, each topic is identified by a group of words having high connection weights from a latent node. In order to facilitate teaming and inferences in multiple-cause models, some approximation methods are required and we utilize an approximation by Helmholtz machines. In an experiment on TDT-2 data set, we extract sets of meaningful words where each set contains some theme-specific terms. Using semantic kernels constructed from latent topics extracted by multiple cause models, we also achieve significant improvements over the basic vector space model in terms of retrieval effectiveness.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.514-528
• /
• 2004

An emotion-based video scene retrieval algorithm is proposed in this paper. First, abrupt/gradual shot boundaries are detected in the video clip representing a specific story Then, five video features such as 'average color histogram' 'average brightness', 'average edge histogram', 'average shot duration', and 'gradual change rate' are extracted from each of the videos and mapping between these features and the emotional space that user has in mind is achieved by an interactive genetic algorithm. Once the proposed algorithm has selected videos that contain the corresponding emotion from initial population of videos, feature vectors from the selected videos are regarded as chromosomes and a genetic crossover is applied over them. Next, new chromosomes after crossover and feature vectors in the database videos are compared based on the similarity function to obtain the most similar videos as solutions of the next generation. By iterating above procedures, new population of videos that user has in mind are retrieved. In order to show the validity of the proposed method, six example categories such as 'action', 'excitement', 'suspense', 'quietness', 'relaxation', 'happiness' are used as emotions for experiments. Over 300 commercial videos, retrieval results show 70% effectiveness in average.

• Cross-Cultural Studies
• /
• v.42
• /
• pp.419-449
• /
• 2016

The Russian icon and Korean tangwha (幀畵, altar portrait of Buddha) are based on the similarity of the divine Being. Each has the characteristic index that forms an existential connection with the object and at the same time, implies the symbolic meaning of the scriptures and doctrines of the Russian Orthodox and Buddhists. Russian icon and Korean tangwha with these attributes have origins in the Byzantine, India and China. Unlike most religious art, Russian icon and Korean tangwha clearly reveal profane orientation and mystical elements. This artistic phenomenon has evolved from the mystical religious culture in Russia and tantric rituals of the early Joseon period. Iconostasis, created from historical figures of the Old Testament, Jesus, the New Testament represent the principles of the macrocosm. Each icon of iconostasis has integrity, while each floor has another narrative and a meta-discourse on the entire composition. Three-Platforms of amrtakundalin can also have a huge epic that is directed from the Low-Platform to the High-Platform for the purpose of salvation. While the narrative of iconostasis has a time structure, from the beginning of the universe up to date in chronological time, amrtakundalin have pictorial transitions of time and space that rises from this life to a heavenly world. Despite the different world views of the Russian Orthodox and Buddhists, iconographical format and symbolism of heaven and hell in the Iconostasis, Last Judgment and amrtakundalin are similar. There is a constant antagonism between heaven and hell, light and darkness, water and flame. Iconographical contents include the water of life and nectar, the book of life and 'eoppu', and the scales and mirror of Karma that discriminate between the good and evil before judgment. The dualistic coordinate concept such as light and darkness, life and death, or heaven and hell that appears in the narrative structure of iconostasis, the Last Judgment and amrtakundalin leads the people to spiritual awakening.

• Science of Emotion and Sensibility
• /
• v.24 no.3
• /
• pp.71-80
• /
• 2021

Previous studies using facial expressions have revealed valence and arousal as two core dimensions of affective space. However, it remains unknown if the two dimensional structure is consistent across ages. This study investigated affective dimensions using six facial expressions (angry, disgusted, fearful, happy, neutral, and sad) at three ages (young, middle-aged, and old). Several studies previously required participants to directly rate subjective similarity between facial expression pairs. In this study, we collected indirect measures by asking participants to decide if a pair of two stimuli conveyed the same emotions. Multidimensional scaling showed that "angry-disgusted" and "sad-disgusted" pairs are similar at all three ages. In addition, "angry-sad," "angry-neutral," "neutral-sad," and "disgusted-fearful" pairs were similar at old age. When two faces in a pair reflect the same emotion, "sad" was the most inaccurate in old age, suggesting that the ability to recognize "sad" decreases with old age. This study suggested that the general two-core dimension structure is robust across all age groups with the exception of specific emotions.