• Korean Journal of Remote Sensing
• /
• v.18 no.2
• /
• pp.71-79
• /
• 2002

This research presents particulate distribution map of tidal flats of Hampyung bay using reflectance which extracted from satellite data and field survey data during same periods. The spectrum of particulate composition obtained from Landsat TM data was analysed and 7 scenes of satellite image were classified with ISODATA and K-MEANS methods. The results of unsupervised classification were estimated with in-situ data. The classification accuracy of ISODATA and K-MAMS methods were 84.3% and 85.7%. For validation of classified results of multi-temporal satellite images, TM image of May 1999(reference data), which was classified with field survey data was compared with classified results of multi-temporary satellite data.

• Journal of Broadcast Engineering
• /
• v.20 no.4
• /
• pp.521-532
• /
• 2015

This paper presents a piecewise image denoising with multi-scale block region detector based on quadtree structure for effective image restoration. Proposed piecewise image denoising method suggests multi-scale block region detector (MBRD) by dividing whole pixels of a noisy image into three parts, with regional characteristics: strong variation region, weak variation region, and flat region. These regions are classified according to total pixels variation between multi-scale blocks and are applied principal component analysis with local pixel grouping, bilateral filtering, and structure-preserving image decomposition operator called relative total variation. The performance of proposed method is evaluated by Experimental results. we can observe that region detection results generated by the detector seems to be well classified along the characteristics of regions. In addition, the piecewise image denoising provides the positive gain with regard to PSNR performance. In the visual evaluation, details and edges are preserved efficiently over the each region; therefore, the proposed method effectively reduces the noise and it proves that it improves the performance of denoising by the restoration process according to the region characteristics.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.23 no.8
• /
• pp.1119-1130
• /
• 1999

The purpose of this was to investigate the differences in recognition of brand and advertisement image according to the life style segments of adolescents. The subjects selected for the final analysis were 613 female high school students whoe were residents in Seoul Pusan and Taejeon. The statistics used for data analysis were factor analysis one-way ANOVA Duncan's multiple range test paired t-test frequency distribution and percentage by the SPSS program The results of this study were as follows : 1. The life style of adolescents wee classified into five groups : Sports Uninterest group Friend Preference/Fashion Uninterest group Sports Preference/Home Oriented group Fashion Interest group and Confidence group. 2, The brand image and advertisement image recognition didn's correspond in general 3. The brand image and advertisement image recognition were significantly different among five groups of life style. The Confidence group and Friend Preference/ Fashion Uninterest group recognized brand image and advertisement image lower than the other groups.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.2
• /
• pp.181-192
• /
• 2002

The purpose of this study is to clarify the expression of conceptual image by which the modern graphic artists use for creating new visual images and the characteristics in expression of the major fashion images in fashion illustration. In the present study, major findings on the basis of the analysis of expression of visual images in fashion illustration since 1980s are as follow: The conceptual image expression in the visual arts is based on the eight techniques. They are dual image, operation of image, copying·reproduction of image, deconstruction of image, pictorial image, symbolization of image, mystification of image, and making humorous image. Since 1980s, the major fashion images in fashion illustration are mainly classified as classic image, humor image, fantastic image, natural image, avant-garde image, simple image, casual image and feminine image. The characteristics in expression of these images in fashion illustration are; 1) fortification of dual image in classic image, 2) activation in humor image 3) grotesque fantastic image, 4) the modernization of natural image, etc. In addition that, the image of avant-garde is expressed by Postermodernism, Deconstructionism, Techno etc. since 1980s. Also, simple image of the modern composition, casual image of daily life, and feminine image which is emphasized with eroticism are also included in these characteristic in expression of images since 1980s.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.263-266
• /
• 2003

In this paper, we propose a new progressive image transmission system including the image coding scheme that efficiently uses the relationship between the properties of a spatial image and its wavelet transform. Firstly, an original image is decomposed into several layers by the wavelet transform, and simultaneously decomposed into 2"x2" blocks. Each image is classified into two image types according to the standard deviations of its blocks. And then each block is categorized into two regions by different thresholds according to the image types, i.e., significant activity region (SAR) and insignificant activity region (IAR). Simulation results show that the proposed coding method has better performance than the EZW and SPIHT in terms of image quality and transmitted bit-rate. In addition, it can be applied to the applications requiring the progressive image transmission.nsmission.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.112-119
• /
• 2019

In this paper, we propose a deep learning structure suitable for embedded system. The flame detection process of the proposed deep learning structure consists of four steps : flame area detection using flame color model, flame image classification using deep learning structure for flame color specialization, $N{\times}N$ cell separation in detected flame area, flame image classification using deep learning structure for flame shape specialization. First, only the color of the flame is extracted from the input image and then labeled to detect the flame area. Second, area of flame detected is the input of a deep learning structure specialized in flame color and is classified as flame image only if the probability of flame class at the output is greater than 75%. Third, divide the detected flame region of the images classified as flame images less than 75% in the preceding section into $N{\times}N$ units. Fourthly, small cells divided into $N{\times}N$ units are inserted into the input of a deep learning structure specialized to the shape of the flame and each cell is judged to be flame proof and classified as flame images if more than 50% of cells are classified as flame images. To verify the effectiveness of the proposed deep learning structure, we experimented with a flame database of ImageNet. Experimental results show that the proposed deep learning structure has an average resource occupancy rate of 29.86% and an 8 second fast flame detection time. The flame detection rate averaged 0.95% lower compared to the existing deep learning structure, but this was the result of light construction of the deep learning structure for application to embedded systems. Therefore, the deep learning structure for flame detection proposed in this paper has been proved suitable for the application of embedded system.

• Fashion & Textile Research Journal
• /
• v.6 no.5
• /
• pp.575-584
• /
• 2004

The purpose of this study was to investigate the differences in recognition of brand and advertisement image according to the advertisement expression forms of domestic make-up cosmetics. This study was conducted by means of a questionnaire survey of female which age from twenties to the thirties. The statistics used for data analysis were frequency distribution, Percentage, mean, factor analysis, and paired t-test by the SPSS program. The results of this study were as follows. The brand and advertisement image of domestic Make-up cosmetics were classified into seven factors. : Of good quality, high-toned, modern, chic, unique, familiar, stimulative brand and advertisement image. The brand image and advertisement image recognition didn't correspond in general except HERCYNA and ETUDE.

• Journal of the Korean Institute of Rural Architecture
• /
• v.14 no.3
• /
• pp.61-68
• /
• 2012

The purpose of this paper is to derive attractive items of 'Hanok' in order to preserve 'Hanok' in urban area, focused on the 13 preceding studies which have got in respect of image, satisfaction, preference, awareness and advantage of 'Hanok' in urban area revolved around the latest studies. This study is analysis of questionnaire items and results of 13 preceding studies. And attractive items are classified with general and overall survey items, advantage of 'Hanok' in urban area, and image of Hanok-density urban area. These can also be classified with 5 items which are space, health, material, form, and image of 'Hanok' in urban area. As a result, Space items are composed with 'use of a space', 'cosiness', 'garden' and 'floor and ondol(korean floor heating system). Health items are composed with 'lighting and ventialtion', 'a sense of the season' and 'natural material'. Material items are composed with 'natural beauty', 'wooden', 'changhoji(traditional Korean paper made from mulberry bark for doors and windows) and hanji(traditional Korean paper handmade from mulberry trees), 'rafter' and 'new materials'. Form items are composed with 'attractive appearance', 'simply decoration' and 'traditional elements'. Image items are composed with 'crowding', 'traditionality and historicity', 'dichroism' and 'warmth'.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.5
• /
• pp.685-694
• /
• 1993

A progressive image transmission (PIT) scheme based on the classified transform vector quantization (CVQ) technique using the lapped orthogonal transform (LOT) and human visual system (HVS) weighting is proposed in this paper. Conventional block transform coding of images using DCT produces in general undesirable block-artifacts at low bit rates. In this paper, image blocks are transformed using the LOT and classified into four classes based on their structural properties and further divided adaptively into subvectors depending on the LOT coefficient statistics with HVS weighting to improve the reconstructed image quality by adaptive bit allocation. The subvectors are vector quantized and transmitted progressively. Coding tests using computer simulations show that the LOT/CVQ based PIT of images is a effective coding scheme. The results are also compared with those obtained using PIT/DCTVQ. The LOT/CVQ based PIT reduces the block-artifacts significantly.

• Journal of Korea Multimedia Society
• /
• v.11 no.8
• /
• pp.1169-1178
• /
• 2008

Most of information in Web2.0 is constructed by users and can be classified by tags which are also constructed and added by users. However, as we known, referring by the related works such as automatic tagging techniques and tag cloud's construction techniques, the research to be classified information and resources by tags effectively is to be given users which is still up to the mark. In this paper, we propose and implement a clustering system that does mapping each other according to relationships of the resource's tags collected from Web and then makes the mapping result into clusters to retrieve images. Tn addition, we analyze our system's efficiency by comparing our proposed system's image retrieval result with the image retrieval results searched by Flickr website.