• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4B
• /
• pp.743-754
• /
• 2000

In this paper, we propose wavelet transform image compression method using shuffling and bit plane correlation. Proposed method is that original image decompose into multiresolutions using biorthogonal wavelet transform with linear phase response property and decomposed subbands are classified by maximum classification gain. And classified data sets in each subband are quantized using arbitrary set optimum bit allocation method. Quantized data sets in each subband are shuffled and context based bit plane arithmetic encoded .In context based bit plane arithmetic encoding, the context for each subband is not assigned uniformly, but assigned according to maximum correlation direction. Our results are comparable, or superior for some images at low rates, to published state-of-the-art coders.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.18-28
• /
• 1997

This paper presents image data compression using a classified vector quantization (CVQ) which categories edge blocks according to the energy distribution of subimages in the discrete cosine transform domain. Classifying the edge blocks enhances visual quality of the compressed images while maintaining a high compression ratio. The proposed classification method categories subimages into eight lypes of edge features according to an energy distribution. A neural network, trained with the data generated from the proposed classification method, can successfully classify subimages to eight edge categories. Experimental results are given to show how the (1VQ method incorporatd with a neural network can produce faithful compressed image quality for high compression ratios.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.588-595
• /
• 2003

High resolution panchromatic satellite images collected by sensors such as IRS-1C/D and KOMPSAT-1 have a spatial resolution of approximately 6 ${\times}$ 6 ㎡, making them very attractive for urban applications. However, the spectral information present in these images is very limited. In order to overcome this limitation, an object-oriented classification approach is used to identify basic land cover types in urban areas. Before an image can be classified it is segmented at different aggregation levels using a multiresolution segmentation approach. In the course of this segmentation various statistical as well as topological information is collected for each segment. Based on this information it is possible to classify image objects and to arrive at much better results than by looking only at single pixels. Using an image recorded by KOMPSAT-1 over the City of Vienna a land cover classification was carried out for two areas. One was used to set up the rules for the different land cover types. The second subset was classified based on these rules, only adjusting some of the functions governing the classification process.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.4
• /
• pp.1-9
• /
• 2018

We propose an emotional training framework that can determine the initial symptom of schizophrenia by using emotional analysis method through facial expression change. We use Emotion API in Microsoft to obtain facial expressions and emotion values at the present time. We analyzed these values and recognized subtle facial expressions that change with time. The emotion states were classified according to the peak analysis-based variance method in order to measure the emotions appearing in facial expressions according to time. The proposed method analyzes the lack of emotional recognition and expressive ability by using characteristics that are different from the emotional state changes classified according to the six basic emotions proposed by Ekman. As a result, the analyzed values are integrated into the image color transfer framework so that users can easily recognize and train their own emotional changes.

• Journal of the Korean Society of Costume
• /
• v.26
• /
• pp.101-121
• /
• 1995

The Purpose of this study was to investigate homology between the Popular music and Fashion of youthful subculture and how the image of popular music have influenced on the 90's fashion. As the result, Korean youthful subculture analized to be different from western youthful subculture. In western countries, the style of youthful subculture groups spread to tricle up as developed themselves but represented tricle down phenomenon in Korea. Because life con-dition of Korean Youthful was different from westerns in everything. The Image of popular music have an influenced on the 90's fashion, it is be classified into the Jazz image, the Country & Western image, the Rock image, and Hip-Hop, Ragge image. 1. The jazz image from Jazz music has come back dandism of the nostalgia mood and intro-duce ethnic sense into fashion. 2. The Country & Western image is reflected in fashion of accessories details, materials and Coordination item. 3. The rock image from Acid Rock and Punk Rock effected the advent of hippie mood fashion, ethnic, ecology, new unisex fashion and Punk fashion trend. 4. The hip-hop, raggae image from Rap and Raggae music showed on fashion of primitive mood's naturism, Sports wear's generalization and dualism. After the 90th, youthful fashion of new gener-ation may be infered constantly on the move toward $\ulcorner Fashion democracy \lrcorner$formation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.6
• /
• pp.468-476
• /
• 2002

The confidence of information from image processing depends on the original image quality. Enhancing the confidence by an algorithm has an essential limitation. Especially, road images are exposed to lots of noisy sources, which makes image processing difficult. We, in this paper, propose a FNN (fuzzy-neural network) capable oi deciding the quality of a road image prior to extracting lane-related information. According to the decision by the FNN, road images are classified into good or bad to extract lane-related information. A CDF (cumulative distribution function), a function of edge histogram, is utilized to construct input parameters of the FNN, it is based on the fact that the shape of the CDF and the image quality has large correlation. Input pattern vector to the FNN consists of ten parameters in which nine parameters are from the CDF and the other one is from intensity distribution of raw image. Correlation analysis shows that each parameter represents the image quality well. According to the experimental results, the proposed FNN system was quite successful. We carried out simulations with real images taken by various lighting and weather conditions and achieved about 99% successful decision-making.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.3
• /
• pp.494-504
• /
• 2008

The purpose of this study was to classify the romantic image by clothing design elements. This research was done by survey method with 20 kinds of romantic image photos selected in fashion magazines. The data was analyzed by Reliability Analysis, Factor Analysis, ANOVA, Duncan's test and MDS. The results of this study are as follows: 1. Romantic image was classified by 4 factors. Those were sexy-romantic, retro-romantic, natural-romantic and cute-romantic images. 2. Sexy-romantic image was well-expressed by fitted silhouette, achromatic and achromatic color coordinations and see-through texture. Retro-romantic image was well-expressed by X silhouette, achromatic and achromatic color coordinations and see-through or combination texture. Natural-romantic image was well-expressed by A silhouette and chromatic and achromatic color coordinations. Cute-romantic image was well-expressed by A silhouette and soft or combination(silky and soft) texture. 3. Romantic image was positioned into mostly traditional or artificial on image scale.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.33 no.1
• /
• pp.160-171
• /
• 2009

The purpose of this study was to classify the classic image by clothing design elements. This research was done by survey method with 20 kinds of classic image photos selected in fashion magazines. The data was analyzed by Reliability Analysis, Factor Analysis, ANOVA, Duncan's test and MDS. The results of this study are as follows: 1. Classic image was classified by 4 factors. Those were retro-classic, mannish-classic, elegant-classic and contemporary-classic images. 2. Retro-classic image was well-expressed by A silhouette and chromatic and chromatic color coordinations. Mannish-classic image was well-expressed by H silhouette, chromatic and achromatic color coordinations and hard texture. Elegant-classic image was well-expressed by fitted silhouette and chromatic and chromatic color coordinations. Contemporary-classic image was well-expressed by achromatic and achromatic color coordinations and hard texture. 3. Classic image was positioned into mostly retro and masculine on image scale.

• Journal of Fashion Business
• /
• v.16 no.6
• /
• pp.127-143
• /
• 2012

This study aims to derive the sensitive image analysing the color tones based on the web-sites of cosmetic brand and to know how the web-site color tones and the color tone image as visual factor for information transfer do influence the effective communication. 10 cosmetic brand web-sites are selected based on the pre survey, and the main page color tones of cosmetic brand web-site are analyzed by Color Catch and Munsell Conversion program, whereas the composition of color tones and color image such as the main trend colors, secondary colors, accent colors and etc are analyzed by a graphic professional program 'Adobe Photoshop'. 5 color tone groups are classified as Black&White, Green&White, Blue&White, Purple&White and Red&White according to the color distribution chart, and the emotional language is derived applying them to the pre research and IRI image scale. The color association is empirically analyzed by a survey method. The study results finally show Black&White is proper for expression of high quality and modern image, Green&White for pure and clean image, Blue&White for cool and transparent image, Purple&White for mysterious and elegant image respectively. This study results are necessary for plan of color delivering the strong transferring power of visual information the time when to make the effective web-sites, and it hopefully will be utilized as the basic data for the color marketing to actively express the brand identity and to satisfy the consumers' sensitivity.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.4
• /
• pp.630-640
• /
• 2008

The purpose of this study was to investigate and make comparison of clothing images presented in women's formal and casual brands. The data were collected from 39 formal brands out of 155 and 64 casual brands out of 256 in Korea Fashion Brand Annual in 2005/2006. 316 words selected were classified into five clothing images according to the definition of previous researches and analyzed according to age ranges and price zones of brands. The results were as follows: 1) Formal brands focused on thirties and forties in age ranges and better and prestige in price zones, while casual brands centered on twenties in age range and better and volume in price zones. 2) Luxury, modem and feminine were more frequent words than others both in formal and casual brands, but elegant was found most frequently in formal brands, while comfortable, chic and simple were found frequently in casual brands. 3) Clothing images were classified into four types and appeared in elegance, modernity, individuality, and activeness order in formal brands, while clothing images in casual brands were classified into five types including youthfulness and appeared in elegance, activeness, modernity, individuality, and youthfulness order. 4) Elegance was a highly presented as clothing image in all the age ranges except thirties of formal brands but modernity and activeness with elegance were presented in price zones of casual brands. This study found that there were differences in clothing images in women's formal and casual brands.