• Journal of the Korean Society of Costume
• /
• v.60 no.7
• /
• pp.61-73
• /
• 2010

This study aims to develop an fashion color design system based on personal color and sensorial images. This web-based system has a parallel structure which a user can search her own personal color, sensorial, and fashion images. The fashion image was presented according to the type of personal color image and sensorial image: futuristic fashion image from alluring image on all of personal color images; elegant fashion images from calm with pure/splendid images or faint/calm with alluring images; modern fashion image from pure/calm with alluring images or faint with lively images; plain fashion image from plain images with all personal color images but pure image; romantic fashion image from calm image with all personal color images but calm image. Fashion color and color combination palettes based on personal color images were presented with the each of those fashion images.

• Journal of Fashion Business
• /
• v.18 no.1
• /
• pp.37-49
• /
• 2014

By investigating structural relationships between personal image and self-efficacy, this experimental study purposes to suggest a direction and the meaning of effective education on personal image. Based on scholars' studies on personal image and self-efficacy, this study extracts a revised questionnaire on personal image. The experimental study proved the relationship between the variables of personal image and self-efficacy by using personal image questionnaires which are extracted from the literature study. For this purpose, we have conducted a questionnaire survey including 234 students from women's university in Seoul. The results of this study are as follows. First, for cognitions on personal image, which are components of the internal image, both the visual image and social image impacting on self-efficacy have a significant efficacy in the self-regulation factor. Second, the satisfaction rates of the components for personal image impacting all the factors of self-efficacy showed a significant effect. Third, the significant results are being obtained from the analysis of differences in self-efficacy according to the levels of satisfaction rates on internal image and social image, which are expected to have effects on the self-efficacy between the groups for all factors. However, according to the analysis of differences in self-efficacy in relation to the levels of satisfaction for visual images, only the self-confidence factor in the self-efficacy is different between the groups.

• Journal of Fashion Business
• /
• v.26 no.3
• /
• pp.98-115
• /
• 2022

The purpose of study was to analyze the process of accepting by BTS fans. The methodology used in this study was qualitative research using grounded theory and the results of the study follow. As a result of open coding, 47 concepts, 23 subcategories, and 14 categories were derived. In the axis coding stage, the casual conditions were "Recognition of BTS image," "Fascinated by BTS image," "Simple consumption of BTS image," and "Arising and expansion of curiosity about BTS image." The contextual conditions were "Accessibility of BTS image" and "Abundance of BTS image searching paths." The central phenomenon appeared to be "Immersing and studying BTS image." The arbitration conditions were "Capabilities required to reproduce BTS image" and "Motivation for contributing BTS image." The actions/interactions were "Presenting BTS image," "Contribution to the spread of BTS image," and "Involved in forming new BTS image." The result was "Emergence and expansion of new BTS image meaning" and "Strengthening attachment to BTS." Through process analysis, it was found that acceptance of BTS images consisted of five stages: "Recognition of BTS image," "Becoming curious about BTS image," "Searching BTS image," "Intervention of BTS image." and "Reproduction of BTS image." As a result of deriving the core categories through selective coding, the core category was "Forming a bond while participating in the BTS image."

• ETRI Journal
• /
• v.29 no.2
• /
• pp.246-248
• /
• 2007

Query-by-example (QBE) is a well-known method for image retrieval. In reality, however, an example image to be used for the query is rarely available. Therefore, it is often necessary to find a good example image to be used for the query before applying the QBE method. Query-by-layout (QBL) is our proposal for that purpose. In particular, we make use of the visual descriptors such as the edge histogram descriptor (EHD) and the color layout descriptor (CLD) in MPEG-7. Since image features of the CLD and the EHD can be localized in terms of a$4{\times}4$ sub-image, we can specify image features such as color and edge distribution on each sub-image separately for image retrieval without a query image. Experimental results show that the proposed query method can be used to retrieve a good image as a starting point for further QBE-based image retrieval.

• Fashion & Textile Research Journal
• /
• v.6 no.6
• /
• pp.715-722
• /
• 2004

The social culture critics say that the current situation of the boom in pretty men happened because stereotyped notions of sex roles have changed. However, no scientific study has been done as yet to support this theory. Therefore, this study analyzed the present situation and examined it from many different points of view. I asked 600 men to fill out the questionnaire: 300 from Daegu and the other 300 from Seoul. I analyzed four 461 of them. The inner/outer image of Korean males in their 20s was analyzed into seven factors, a positive image, a progressive image, an affirmative image, a sensible image, an exemplary image, a conscious image, and an active image. The demographic result based on the inner/outer image factors showed a significant difference in ages for a sensible image, a conscious image, and an active image.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.18 no.2
• /
• pp.170-179
• /
• 1994

The purpose of this study was to identify the constructing factors and the hierarchy of the female clothing image evaluation made by male university students. 'rho instruments developed by the precedent study of In Hee Chung(1992) was used compare the female clothing image evaluation made by male university students with that by (emale students. The results were 1. 5 factor - modernity, grace, activeness, uniqueness, masculinity were found out as constructors of female clothing image evaluation made by male university student. 2. Eleven clusters were determinted to exist. The clusters classified as the main groups were 'modem and romantic image' and 'classic and straight image.'

• Journal of the Korean Society of Costume
• /
• v.61 no.2
• /
• pp.47-59
• /
• 2011

This study provides a systematic investigation about objective personal image consulting, tool development and image-making research by analyzing the status of the Korean image-consulting industry and education. For the research, we carried out literature surveys of books on image consulting and previous research reports. In particular, we surveyed image consulting businesses that have internet web sites, and educational institutes. The results of the survey are as follows: First, domestic image consulting businesses in Korea are investigated about 93 private companies and 4 associations. They do the image making, color consulting, and education for individuals and business. Second, professional image consulting education is carried out not only in the 93 private companies, but also in the continuing and professional studies for adults of 10 universities. Furthermore, more then 90 universities have specific academic programs related to the image consulting such as facial management, beauty coordination, cosmetology, stylists, fashion events, broadcasting stylists, and so on. Third, a typical image consulting job is the personal shoppers who assists VIP customers in department stores. Professionals and politicians have personal fashion stylists for their image making. Today, the job has expanded to public fashion therapist. Fourth, the contents of an image consulting education have appeared in similar industries and educations. These contents include fashion styles, personal color analysis, make-up, facial expressions, gestures, perfumes, accessories, etc. This study is based on research on the current Korean image-consulting industry, and will enable follow-up details to be implemented. using the basis of this study for a strategic self-image formation system.

• Journal of Ubiquitous Convergence Technology
• /
• v.2 no.1
• /
• pp.18-26
• /
• 2008

The invariance relation existing in the non-negative matrix factorization (NMF) is used for constructing robust image hashes in this work. The image is first re-scaled to a fixed size. Low-pass filtering is performed on the luminance component of the re-sized image to produce a normalized matrix. Entries in the normalized matrix are pseudo-randomly re-arranged under the control of a secret key to generate a secondary image. Non-negative matrix factorization is then performed on the secondary image. As the relation between most pairs of adjacent entries in the NMF's coefficient matrix is basically invariant to ordinary image processing, a coarse quantization scheme is devised to compress the extracted features contained in the coefficient matrix. The obtained binary elements are used to form the image hash after being scrambled based on another key. Similarity between hashes is measured by the Hamming distance. Experimental results show that the proposed scheme is robust against perceptually acceptable modifications to the image such as Gaussian filtering, moderate noise contamination, JPEG compression, re-scaling, and watermark embedding. Hashes of different images have very low collision probability. Tampering to local image areas can be detected by comparing the Hamming distance with a predetermined threshold, indicating the usefulness of the technique in digital forensics.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12spc
• /
• pp.463-468
• /
• 2021

Single image super-resolution (SISR) is an image processing technique, and its main target is to reconstruct the high-quality or high-resolution (HR) image from the low-quality or low-resolution (LR) image. Currently, deep learning-based convolutional neural network (CNN) image super-resolution approaches achieved remarkable improvement over the previous approaches. Furthermore, earlier approaches used hand designed filter to upscale the LR image into HR image. The design architecture of such approaches is easy, but it introduces the extra unwanted pixels in the reconstructed image. To resolve these issues, we propose novel deep learning-based approach known as Lightweight deep CNN-based approach for Single Image Super-Resolution (LDCSIR). In this paper, we propose a new architecture which is inspired by ResNet with Inception blocks, which significantly drop the computational cost of the model and increase the processing time for reconstructing the HR image. Compared with the other state of the art methods, LDCSIR achieves better performance in terms of quantitively (PSNR/SSIM) and qualitatively.