• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.13-23
• /
• 2022

In this paper, we propose a detailed component image classification algorithm by fashion item for unstructured data retrieval in the fashion field. Due to the COVID-19 environment, AI-based online shopping malls are increasing recently. However, there is a limit to accurate unstructured data search with existing keyword search and personalized style recommendations based on user surfing behavior. In this study, pre-processing using Mask R-CNN was conducted using images crawled from online shopping sites and then classified components for each fashion item through CNN. We obtain the accuaracy for collar of the shirt's as 93.28%, the pattern of the shirt as 98.10%, the 3 classese fit of the jeans as 91.73%, And, we further obtained one for the 4 classes fit of jeans as 81.59% and the color of the jeans as 93.91%. At the results for the decorated items, we also obtained the accuract of the washing of the jeans as 91.20% and the demage of jeans accuaracy as 92.96%.

• The Research Journal of the Costume Culture
• /
• v.15 no.5
• /
• pp.825-837
• /
• 2007

To analyze the design of Christian Dior, 216 pieces of Dior's works were collected and studied from the COLLECTION(Seoul: Dong Ah TV) from 2003 to 2005. The result is as follows. In recent three year period, Christian Dior maintained the feminine image and implemented different additions such as sexy, ethnic, avant-garde and casual image in every season. Also, to reflect a new trend or fashion sense, images of ethnic, retro, hippie or vintage were applied. In using color, different main color(YR, R, Y, BG, RP, B) were chosen every season to pursue variations. For the pattern usage, feminine beauty was presented by numerous applications of flowered pattern. Also the practice of pattern and hue in different rations in every season pursued variations in design.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.22 no.1
• /
• pp.61-71
• /
• 1998

The purpose of this study was to identify the factors which explain consumer's information search behavior. Data were analyzed by utilizing factor analysis and multiple-regression to investigate the relationship among information sources, benefit, and actual and ideal self- image and demographics. Based on the results, information sources for benefit, actual and ideal self-image were developed. Predictors of information sources, benefits, and self-image were identified. Marketing implication about information sources were discussed. The results were as follows. 1. Actual and ideal self-images and information sources were devised into three factors. And benefits were devised into five factors. 2. Actual self-image has more predicting power than ideal self-image to the benefits which consumer sought. Among five benefits, character pursuit was the best predicted factor according to the self-image. 3. Among three information sources, mass communication was the most effective source which can be explained by the benefit and self-image. Fashion pursuit factor was the most significant factor to the mass communication oriented source.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.33 no.8
• /
• pp.1325-1336
• /
• 2009

This study is to find the interpretation of Korean aesthetics with emotional, relative, synthetic thinking in the ambiguity of characteristics of multi-culturalism and ambivalence in contemporary beauty design. Beauty design incorporates makeup and hair design to complete the total images with clothing in fashion shows and Korean aesthetics based on Korean religion and art that include the symbolism of humor, irregularity, moderation, harmony, unification, and emptiness. This study analyzes 864 works of make-up and hair design from 2001 S/S to 2009 F/W to understand the beauty design to summarize the natural, eclectic, classic, poor, humor, and decadent tendencies. The characteristics of aesthetics sense of Beauty Design are summarized as artless naturalism, integrate pluralism, de-constructive deviation, and temperate poverty.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.11
• /
• pp.1534-1541
• /
• 2003

A new window-based, user-friendly fringe analysis system is developed, especially for analyzing noisy interferograms. The system integrates three major techniques, that is fringe tracking, Phase shifting, and Fourier transform, into a single shell by employing a unified procedure. Since the system is made in a modular fashion and all processing modules can be shared for any technique, a user can select necessary modules and easily edit the applying order of them based on the user's analysis strategy, which should be changed depending on the noise level of the image. The system provides a high-level GUI and a variety of image handling tools and therefore users can easily access the system and produce the optimal results without giving up in the middle of a process even for severely noise-contaminated interferometric images.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.22 no.2
• /
• pp.233-240
• /
• 1998

The main objective of this study was to develop a basic information base on Chinese consumers related to clothing purchases. Previous studies on Chinese consumers were extensively reviewed and in-depth interviews were conducted with 12 middle-level managers at Korean apparel companies which market their merchandises in China. Combined results from the reviews on previous studies and interviews indicated that traditional values, communism and industrialization are the major forces which shape contemporary Chinese consumers. Industrialization, in particular, accompanied by influx of western culture and economic development, has resulted in wide-spread phenomenon of conspicuous consumption. Thus, brand and brand images appeared to be the most important considerations for purchasing imported apparels. In addition, diversity of Chinese consumers and geographical differences were emphasized, which indicated need for market segmentation. Other characteristics including body measurements also provided implications for fashion marketing in China.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.24 no.7
• /
• pp.976-986
• /
• 2000

The purpose of this study is to clarify the relationship between the visual sensibility and the decorative design of clothing. 41 kinds of costume samples have been selected from photographs in fashion magazines under detail and trimming, and divided into three types according to line, shape, and form. I have measured these images by using Semantic Differential method. The obtained data were analyzed by factor analysis ANOVA, discriminant analysis, regression analysis and MDS. The results of analysis are as follow; 1. Factor analysis has extracted five factors which consist of decorative design sensibility. These factors are Attractiveness, Hardness and Softness, Rhythm, Decorativeness, Cuteness. 2. There were significant differences in visual evaluation of decorative design and demographics 3. The discrimination among formative designs was closely related to decorative image, especially between line and form. 4. The Image effect on Preference, Buying needs, Riches and Pleasant was consist of complicated sensibility. 5. Evaluative dimensions of decorative design were identified by Simple-Complicated, Cubic -Plane perceptive image differed in degree of similarity in spite of same formative design.

• Korean Journal of Materials Research
• /
• v.27 no.9
• /
• pp.484-488
• /
• 2017

In the present study, domain evolution processes of a near-morphotropic PZT ceramic during poling was studied using vertical piezoresponse force microscopy (PFM). To perform macroscopic poling in bulk polycrystalline PZT, poling was carried out in a stepwise fashion, and PFM scan was performed after unloading the electric field. To identify the crystallographic orientation and planes for the observed non-$180^{\circ}$ domain walls in the PFM images, compatibility theory and electron backscatter diffraction (EBSD) were used in conjunction with PFM. Accurate registration between PFM and the EBSD image quality map was carried out by mapping several grains on the sample surface. A herringbone-like domain pattern consisting of two sets of lamellae was observed; this structure evolved into a single set of lamellae during the stepwise poling process. The mechanism underlying the observed domain evolution process was interpreted as showing that the growth of lamellae is determined by the potential energy associated with polarization and an externally applied electric field.

• Applied Microscopy
• /
• v.46 no.2
• /
• pp.100-104
• /
• 2016

Electron microscopy is currently the only available technique with a spatial resolution sufficient to identify fine neuronal processes and synaptic structures in densely packed neuropil. For large-scale volume reconstruction of neuronal connectivity, serial block-face scanning electron microscopy allows us to acquire thousands of serial images in an automated fashion and reconstruct neural circuits faster by reducing the alignment task. Here we introduce the whole reconstruction procedure of synaptic network in the rat hippocampal CA1 area and discuss technical issues to be resolved for improving image quality and segmentation. Compared to the serial section transmission electron microscopy, serial block-face scanning electron microscopy produced much reliable three-dimensional data sets and accelerated reconstruction by reducing the need of alignment and distortion adjustment. This approach will generate invaluable information on organizational features of our connectomes as well as diverse neurological disorders caused by synaptic impairments.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.7-13
• /
• 2021

Machine vision is a technology that helps the computer as if a person recognizes and determines things. In recent years, as advanced technologies such as optical systems, artificial intelligence and big data advanced in conventional machine vision system became more accurate quality inspection and it increases the manufacturing efficiency. In machine vision systems using deep learning, the image quality of the input image is very important. However, most images obtained in the industrial field for quality inspection typically contain noise. This noise is a major factor in the performance of the machine vision system. Therefore, in order to improve the performance of the machine vision system, it is necessary to eliminate the noise of the image. There are lots of research being done to remove noise from the image. In this paper, we propose an autoencoder based machine vision system to eliminate noise in the image. Through experiment proposed model showed better performance compared to the basic autoencoder model in denoising and image reconstruction capability for MNIST and fashion MNIST data sets.