• Journal of the Korean Society of Clothing and Textiles
• /
• v.41 no.4
• /
• pp.661-672
• /
• 2017

This research studies the aesthetic value of typography in fashion, within the framework of system for objective and multilateral research. For this purpose, a literature review and analysis of system and typography were performed. The scope of this research is from 2000 to 2015. The results of the research can be summarized as follows. First, by analyzing system and typography in modern fashion in order to set up a new theoretical standard, we found that the main values of typography in modern fashion concern functionality, hierarchy, stability, independency, and flexibility. Second, by analyzing of aesthetic value of typography in fashion within system, we found that main values the functionality of typography as a marketing tool, the hierarchy of typography as a slogan of subculture, the stability of typography for the increasing of collective belonging, the independency of typography as a linguistic playfulness, and the flexibility of typography as an image. Lastly, each aesthetic value of typography expressed in fashion has similarities and differences. It could be considered in the same vein as the system that always has a double-side character of dependency and independency, universality and individuality. This study has pursued to conduct more research on fashion within a framework of system.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.5
• /
• pp.715-726
• /
• 2002

The purpose of this study was to investigate the visual sensibility of color combination for clothing. The color combination for clothing were divided into three types according to the color coordination. In each type, the stimulus was applied three combination method according to the chromatic color/chromatic color, the chromatic color/achromatic color, the achromatic color/achromatic color. As a result, 42 color combination for clothing were obtained. The survey has been done for the 42 color combination for clothing with 27 semantic differential hi-polar scales. The major findings of this research were as follows. 1. To explain the hierarchy of visual sensibility, two sensibility groups were classified, the first group being cute and bold sensibility and the second group being comfortable and soft sensibility. 2. As result of the factor analysis, 4 factors(attractiveness, cuteness, boldness, softness) were found to be constructing factors for visual sensibility of color combination for clothing. 3. To explain the hierarchy of visual sensibility, two sensibility groups were classified, the first group being cute and bold sensibility and the second group being comfortable and sort sensibility.

• Journal of the Korean Society of Costume
• /
• v.53 no.4
• /
• pp.1-16
• /
• 2003

The purpose of this study is to investigate the sensibility images of Korean Traditional Chumoni. The detailed methodology of this study is as follows. Selections of stimuli to analyse the sensibility images of Korean Traditional Chumoni were made up of 15 stimuli. The survey has been done for the 15 slide stimuli with semantic differential hi-polar scales which are consist of 23 couples of sensibility words. The subjects were 150 female students majoring in clothing and textile. 150 male students majoring in other department and 150 female students majoring in other department in the twenties between 2001. 3. 30 and 2001. 4. 4. The obtained data were analyzed by factor analysis, cluster analysis. ANOVA. The major finds were as follows. 1. To explain the hierarchy of the sensibility of Korean Traditional Chumoni, two image groups were classified, one is noble and characteristic image the other is splendid and intensive image. Finally it represented noble and splendid image. 2. As result of the factor analysis. 3 factors which are Attraction, Decorativeness, Gravity were found to be constructing factors for the sensibility images of Korean Traditional Chumoni. 3. By cluster analysis, 4 clusters were determined according to Korean Traditional Chumoni. Cluster 1 is splendid. multi-colored and realistic in patteren. Cluster 2 is consist of 'true chumonis' and one-colored. Cluster 3 is modal in pattern. Cluster 4 is simple without any decorations. As to the difference of image of Korean Traditional Chumoni, there were significant differences amang 3 factors by cluster Cluster 1 was found most attractive and grave. Cluster 2 was found most decorative. 4. As to the difference of image of Korean Traditional Chumoni, there were significant differences amang 3 factors by decoration. Gold foil was found most attractive and grave. Embroidery was found most decorative. 5. As to the difference of image of Korean traditional chumoni, there were differences in Decorativeness and Gravity by sex and there were differences in Attraction by major.

• Korean Journal of Human Ecology
• /
• v.17 no.4
• /
• pp.733-744
• /
• 2008

In this research, we investigated the university students' consciousness and preference for the jacquard fabrics and developed the evaluation scale of the sensibility of jacquard fabrics appied by Korean traditional motives. 23 jacquard fabrics were assessed subjectively by 466 consumers using the 7-point scale of 23 descriptors of texture sensibility and 50 descriptors image sensibility. The percentage of students who were interested in jacquard fabrics was similar as that of students who were uninterested. 75.3% of students were shown to think that it was necessary to apply Korean traditional motives to the jacquard fabrics. Through cluster analysis, the hierarchy of the image sensibility was examined. The tactile sensibility of jacquard fabrics were classified into 9 sub-clusters, image sensibility of them were classified into 14 sub-clusters. The dimensions evaluating the image sensibility of jacquard fabrics were developed using multi-dimensional scaling method. A 3-dimensions and 6-axes system were determined, which consisted of 'classic-modern', 'splendid-plain', 'abstract-realistic'. It was shown that preference of jacquard fabrics was increased, as image sensibility such as 'various', 'gorgeouse', 'beautiful', 'mild', 'dim', 'traditional', 'orderly', 'comfortable', 'dignified', 'abundant', 'fantastic', and 'vague' were increased and those such as 'intense', 'old', 'stuffy', 'exotic' and 'static' were decreased.

• Journal of Internet Computing and Services
• /
• v.6 no.2
• /
• pp.59-68
• /
• 2005

In this paper, for compression and transmission of 3D image, we propose an algorithm which executes 3D discrete cosine transform(DCT) for 3D images, hierarchically segments 3D blocks of an image in comparison with the original image and executes finite-state vector quantization(FSVQ) for each 3D block. Using 3D DCT coefficient feature, a 3D image is segmented hierarchically into large smooth blocks and small edge blocks, then the block hierarchy informations are transmitted. The codebooks are constructed for each hierarchical blocks respectively, the encoder transmits codeword index using FSVQ for reducing encoded bit with hierarchical segmentation information. The new algorithm suggested in this paper shows that the quality of Small Lobster and Head image increased by 1,91 dB and 1.47 dB respectively compared with those of HFSVQ.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.451-458
• /
• 2015

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.515-518
• /
• 2019

Semantic segmentation has remained as a challenging problem in the field of computer vision. Given the immense power of Convolution Neural Network (CNN) models, many complex problems have been solved in computer vision. Semantic segmentation is the challenge of classifying several pixels of an image into one category. With the help of convolution neural networks, we have witnessed prolific results over the time. We propose a convolutional neural network model which uses Fully CNN with deconvolutional pixel layers. The goal is to create a hierarchy of features while the fully convolutional model does the primary learning and later deconvolutional model visually segments the target image. The proposed approach creates a direct link among the several adjacent pixels in the resulting feature maps. It also preserves the spatial features such as corners and edges in images and hence adding more accuracy to the resulting outputs. We test our algorithm on Karlsruhe Institute of Technology and Toyota Technologies Institute (KITTI) street view data set. Our method achieves an mIoU accuracy of 92.04 %.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.333-336
• /
• 2007

We propose a simple method for tracking a nonparameterized subject contour in a single video stream with a moving camera and changing background. Then we present a method to eliminate the tracked contour object by replacing with the background scene we get from other frame. Our method consists of two parts: first we track the object using LOD (Level-of-Detail) canny edge maps, then we generate background of each image frame and replace the tracked object in a scene by a background image from other frame that is not occluded by the tracked object. Our tracking method is based on level-of-detail (LOD) modified Canny edge maps and graph-based routing operations on the LOD maps. To reduce side-effects because of irrelevant edges, we start our basic tracking by using strong Canny edges generated from large image intensity gradients of an input image. We get more edge pixels along LOD hierarchy. LOD Canny edge pixels become nodes in routing, and LOD values of adjacent edge pixels determine routing costs between the nodes. We find the best route to follow Canny edge pixels favoring stronger Canny edge pixels. Our accurate tracking is based on reducing effects from irrelevant edges by selecting the stronger edge pixels, thereby relying on the current frame edge pixel as much as possible. This approach is based on computing camera motion. Our experimental results show that our method works nice for moderate camera movement with small object shape changes.

• Journal of KIISE:Databases
• /
• v.30 no.5
• /
• pp.494-506
• /
• 2003

Recently, explosive popularity of multimedia information has triggered the need for retrieving multimedia contents efficiently from the database including audio, video and images. In this paper, we propose an XML-based retrieval scheme and a data model that complement the weak aspects of annotation and conent based retrieval methods. The Property and hierarchy structure of image and video data are represented and manipulated based on the Multimedia Description Schema (MDS) that conforms to the MPEG-7 standard. For audio contents, pitch contours extracted from their acoustic features are converted into UDR string. Especially, to improve the retrieval performance, user's access pattern and frequency are utilized in the construction of an index. We have implemented a prototype system and evaluated its performance through various experiments.

• Convergence Security Journal
• /
• v.18 no.4
• /
• pp.19-25
• /
• 2018

In this paper, we propose an user-centered integrated lost-goods management system through a ranking system based on weight and a hierarchical image classification system based on Deep Learning. The proposed system consists of a hierarchical image classification system that automatically classifies images through deep learning, and a ranking system modules that listing the registered lost property information on the system in order of weight for the convenience of the query process.In the process of registration, various information such as category classification, brand, and related tags are automatically recognized by only one photograph, thereby minimizing the hassle of users in the registration process. And through the ranking systems, it has increased the efficiency of searching for lost items by exposing users frequently visited lost items on top. As a result of the experiment, the proposed system allows users to use the system easily and conveniently.