• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.455-458
• /
• 2001

In this paper, a new license plate recognition method using the morphological size distribution functions and color images is proposed. The proposed method consists of two steps. The first step is license plate extraction process using the plate color and step edge information in the license plate. The second step is the extraction of character feature vectors using the morphological size distribution functions and character recognition process using the MLP(multilayer perceptron). By the use of morphological size distributions functions, the error that may occur during the character region extraction process is lessened and the recognition performances are improved by the decrease of feature vector dimension.

• Journal of Food Hygiene and Safety
• /
• v.12 no.4
• /
• pp.346-353
• /
• 1997

This study was undertaken to find out distribution and contamination sources of hazardous microbes through microbial hazard analysis on the processing steps of surimi-based imitation crab (SBIC). As a results of ananlysis of 9 hazardous microbes for 16 raw materials and 8 processing steps, no Samonella spp. and Escherichia coli were detected in all samples. Level and distribution of hazardous microbes in mixed color were similar to those of surimi. Changes of aerobic plate counts (APC), psychrotropic bacteria, coliforms, Staphylococcus aureus and Vibrio parahaemolyticus showed similar trends at different processing steps. Thermotrophic bacteria and aerobic sporeformers were not detected until mixing step and feeding step, respectively and not reduced after cooking step. According to the comparison of APC at each step, it was suggested that surimi, workers and silent cutter at mixing step, and mixed color, workers and bundler at packaging step were the major contamination sources of bacteria.

• Korean Journal of Plant Taxonomy
• /
• v.41 no.3
• /
• pp.271-279
• /
• 2011

The morphological characteristics of the Korean Scopolia japonica Maxim., commonly known as 'Mi-chi-gwang-i-pul' in Korean, were re-evaluated in comparison with results from previous research, while the distribution map was formulated according to existing flora and voucher specimens. The result of the re-evaluation has shown that there are some distinctive discrepancies compared to the previous reports of some characteristics such as the color of the basal stem, numbers of lateral veins, apex shape of calyx and corolla including the color of corolla. The Korean Scopolia japonica Maxim is found throughout Korea except Jeju-do province. The intra-specific species such as S. parviflora (Dunn.) Nakai, S. lutescens Y.N. Lee and S. kwangdokensis Y.N. Lee were treated as synonyms of S. japonica Maxim. in this research.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.12 no.3
• /
• pp.1-15
• /
• 2010

The purpose of this study is to clarify of the distribution routes of cosmetics by their types and differences in choosing them according to ages with the ones in choosing brand by the type according to them. The subjects of the study were females aged 20 plus living in Seoul and Gyeonggi Province between January and February 2008, and 427 questionnaires were used for analysis. For data analysis SPSS 17.0 statistical program was used, and principal component analysis, frequency analysis, ${\chi}^2-test$, ANOVA test and Duncan test were conducted. The results and conclusions of this study are as follows: first, cosmetics store use by product type was examined. Department stores were used most often to purchase skincare, base and color products, while large cosmetics stores were used most frequently to buy hair and body products. Second, The result of the differences in choosing brand by type of cosmetics has found that there are the meaningful differences between Korean low and middle priced brands and foreign high priced ones in skincare and base products. The Korean low and middle priced brands of skin care products show that various distribution routes are simultaneously and highly used as choices in internet, cosmetics specialty stores and large general ones are higher than other distribution routes. Color products have found that there are the meaningful differences in the entire brands. Hair and body products have found that there are the meaningful differences in three brands except the Korean high priced brands. Third, the differences in cosmetics store selection by age were investigated. As for online purchasing, people in their 20's were most likely than other age groups to purchase online. Meanwhile, in case of other stores including door-to-door sales and home shopping, people aged 40 and older were more prone than other age groups to purchase base, color and body products through these stores.

• Analytical Science and Technology
• /
• v.32 no.3
• /
• pp.77-87
• /
• 2019

High viscosity carbon black dispersions are used in various industrial fields such as color cosmetics, rubber, tire, plastic and color filter ink. However, carbon black particles are unstable to heat due to inherent characteristics, and it is very difficult to keep the quality of the product constant due to agglomeration of particles. In general, particle size analysis is performed by dynamic light scattering (DLS) during the dispersion process in order to select the optimum dispersant in the carbon black dispersion process. However, the existing low viscosity analysis provides reproducible particle distribution analysis results, but it is difficult to select the optimum dispersant because it is difficult to analyze the reproducible particle distribution at high viscosity. In this study, dynamic light scattering (DLS) and asymmetrical flow field-flow fractionation (AsFlFFF) analysis methods were compared for reproducible particle size analysis of high viscosity carbon black. First, the stability of carbon black dispersion was investigated by particle size analysis by DLS and AsFlFFF according to milling time, and the validity of analytical method for the selection of the optimum dispersant useful for carbon black dispersion was confirmed. The correlation between color and particle size of particles in high viscosity carbon black dispersion was investigated by using colorimeter. The particle size distribution from AsFlFFF was consistent with the colorimetric results. As a result, the correlation between AsFlFFF and colorimetric results confirmed the possibility of a strong analytical method for determining the appropriate dispersant and milling time in high viscosity carbon black dispersions. In addition, for nanoparticles with relatively broad particle size distributions such as carbon black, AsFlFFF has been found to provide a more accurate particle size distribution than DLS. This is because AsFlFFF, unlike DLS, can analyze each fraction by separating particles by size.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.1-12
• /
• 2009

The correct detection of skin color is an important preliminary process in fields of face detection and human motion analysis. It is generally performed by three steps: transforming the pixel color to a non-RGB color space, dropping the illuminance component of skin color, and classifying the pixels by the skin color distribution model. Skin detection depends on by various factors such as color space, presence of the illumination, skin modeling method. In this paper we propose a 3d skin color model that can segment pixels with several ethnic skin color from images with various illumination condition and complicated backgrounds. This proposed skin color model are formed with each components(Y, Cb, Cr) which transform pixel color to YCbCr color space. In order to segment the skin color of several ethnic groups together, we first create the skin color model of each ethnic group, and then merge the skin color model using its skin color probability. Further, proposed model makes several steps of skin color areas that can help to classify proper skin color areas using small training data.

• Journal of Distribution Science
• /
• v.14 no.8
• /
• pp.139-151
• /
• 2016

Purpose - In Chinese rose market, Korea competes against Latin American and African countries, but is not so competitive in terms of price and quality, implying the importance of using appropriate marketing strategies. This study aims to examine Chinese rose consumers' recognition and attributes of preference for roses produced in Korea, in order to use the result as baseline data for Korean rose exporters to China and provide implications that help establish a variety of marketing strategies targeting each region, income and age group. Research Design, Data and Methodology - 112 Chinese people were involved and interviewed in Chinese horticulture industry who had participated in 2016 Hortiflorexpo IPM Beijing. Online questionnaire survey was additionally conducted with 533 Chinese living in Korea and China. The Conjoint Analysis was conducted for region, age, and income group of respondents to estimate the relative importance of rose attributes evaluated by each population group and the utility derived from each attribute level. This process aimed to compare respective population groups for the relative importance and utility to derive implications for targeted marketing strategies. Results - The analysis finds that Chinese rose consumers prioritize rose color, followed by price, flowering stage, and flower size in purchasing roses. They prefer red roses most, followed by pink and then yellow. Moreover, they prefer larger roses, and relatively cheaper roses. The analysis reveals they prefer roses in their 20%-flowering stage to more than 40%-flowering stage. Conclusions - Establishing marketing strategies differentiated for each Chinese consumer group is critical in expanding Korean rose export. The analysis finds while Chinese consumers living in Beijing considered rose color and flowering stage more importantly than their counterparts in Shanghai, Chinese consumers living in Shanghai considered rose price and size more importantly than their counterparts living in Beijing. Therefore, establishing marketing strategies based on these attributes of preference in each region is necessary. Mid & low-income consumer groups considered price as the most important factor, and high-income consumer groups considered rose color as the most important one. It is, thus, important to focus on rose color when establishing a marketing strategy with targeting the high-income consumer group.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.11
• /
• pp.2083-2090
• /
• 2008

In this paper, we propose a method for control of temperature and the direction of wind in an air-cooler using thermal images and fuzzy inference rules in order to achieve energy saving. In a simulation for controlling temperature, a thermal image is transformed to a color distribution image of $300{\times}400$ size to analyze the thermal image. A color distribution image is composed of R, G and B values haying temperature values of Red, Magenta, Yellow, Green, Cyan and Blue. Each color has a temperature value from $24.0^{\circ}C$ to $27.0^{\circ}C$ and a color distribution image is classified into height hierarchies from level 1 to level 10. The classified hierarchies have their peculiar color distributions and temperature values are assigned to each level by temperature values of the peculiar colors. The process for controlling overall balance of temperature and the direction of wind in an indoor space is as follows. Fuzzy membership functions are designed by the direction of wind, duration time, and temperature and height values of a color distribution image to calculate the strength of wind. After then, the strength of wind is calculated by membership values of membership functions.

• Journal of Fashion Business
• /
• v.13 no.6
• /
• pp.61-75
• /
• 2009

The objective of this research is to the enhance the color function of work clothing : to research and analyze the hue and tone of work clothing colors to be used for machinery and heavy industries in national industrial complexes, Through this research, the color using problems which related with safety workers will be revealed. For this project, total 42 sets of work suits were sampled from 12 different companies in the machinery and construction industries in the national industrial complexes of Gyeongsang Namdo Province and 16 sets of work suits currently being sold in the market. The collected work suits samples were classified according to item types and design. Color measurements were taken thus: After calibration according to ASTM D1729 specifications of standardized configuration settings to match standardized luminous source D65(Daylight 6500K) in color cabinet BOTECK SuperLight-VI, the RGB values of the work suits were calculated using PANTONE Color Cue TX. The RGB values of the colors thus derived were converted into V/C values using the Munsell Conversion 9.0.6 and analyzed with Munsell's 10-color system and PCCS. The results were presented according to Munsell's color wheel and color and brightness distributions were expressed in table form, as well as presented as a tone map. Following analysis, color hue distribution was found to be concentrated around PB, and brightness distribution toward the low end and mid range of the scale. Saturation values were distributed mostly around the low end of the scale. Following color tone analysis according to PCCS, it became apparent that colors were mainly distributed around dkg, ltg, and g, at low- and mid-brightness and low-saturation. Therefore, it may be concluded that colors used in work suits in the machinery and heavy industries are mainly cool colors, at low- and mid-brightness and low saturation. It is conjectured that such colors were applied uniformly in the workplace in order to serve certain functions, such as concealment of stains and contamination. Therefore, it follows that the utilization of colors, among other functions served by working clothings, must be taken into consideration in order to enhance safety and efficiency.

• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.689-698
• /
• 2006

Pattern recognition is the study of how machines can observe the environment, learn to distinguish patterns of interest from their background, and make sound and reasonable decisions about the categories of the patterns. Color image consists of various color patterns. And most pattern recognition methods use the information of color which has been trained and extract the feature of the color. This thesis extracts adaptively specific color feature from images with several limited colors. Because the number of the color patterns is limited, the distribution of the color in the image is similar. But, when there are some noises and distortions in the image, its distribution can be various. Therefore we cannot extract specific color regions in the standard image that is well expressed in special color patterns to extract, and special color regions of the image to test. We suggest new method to reduce the error of recognition by extracting the specific color feature adaptively for images with the low distortion, and six test images with some degree of noises and distortion. We consequently found that proposed method shouws more accurate results than those of statistical pattern recognition.