• Journal of the Korea Society of Computer and Information
• /
• v.18 no.6
• /
• pp.21-28
• /
• 2013

This paper proposes an effective fire detection approach that includes the following multiple heterogeneous algorithms: moving region detection using grey level histograms, color segmentation using fuzzy c-means clustering (FCM), feature extraction using a grey level co-occurrence matrix (GLCM), and fire classification using support vector machine (SVM). The proposed approach determines the optimal threshold values based on grey level histograms in order to detect moving regions, and then performs color segmentation in the CIE LAB color space by applying the FCM. These steps help to specify candidate regions of fire. We then extract features of fire using the GLCM and these features are used as inputs of SVM to classify fire or non-fire. We evaluate the proposed approach by comparing it with two state-of-the-art fire detection algorithms in terms of the fire detection rate (or percentages of true positive, PTP) and the false fire detection rate (or percentages of true negative, PTN). Experimental results indicated that the proposed approach outperformed conventional fire detection algorithms by yielding 97.94% for PTP and 4.63% for PTN, respectively.

• Culinary science and hospitality research
• /
• v.16 no.4
• /
• pp.238-246
• /
• 2010

This study investigates the quality characteristics of soybean dasik made with various levels(0, 3, 6, 9 and 12%) of Platycodon grandiflorum(Jacq.) A. DC. flour additions. In soybean dasik added with Platycodon grandiflortum(Jacq.) A. DC flour, moisture contents range from $24.47{\pm}0.35$ to $26.31{\pm}0.81%$ As Platycodon grandiflorum(Jacq.) A. DC flour increased, lightness values were decreased and redness and yellowness values were increased significantly. The result of the mechanical evaluation showed that hardness increased after significantly decreasing while adhesiveness, gumminess and chewiness decreased with the amount of Platycodon grandiflorum(Jacq.) A. DC flour increased. Cohesiveness and springiness did not change significantly according to Che level of Platycodon grandiflorum(Jacq.) A. DC flour. In conclusion, soybean dasik with the addition of 6% Platycodon grandiflorum(Jacq.) A. DC flour has the most propper taste, flavor and overall acceptability on sensory evaluation.

• Journal of Fashion Business
• /
• v.19 no.2
• /
• pp.53-68
• /
• 2015

The Beijing Opera is one of the leading representatives of Chinese culture, which includes literature, music, dance, martial arts, and a type of performance that stems from the Chinese cultural history that is still relevant today. The purpose of this study is to develop fashion-cultural products from the Lian Pu of the Beijing Opera, a Chinese cultural tradition that receives abundant positive feedback from around the world, showing its value in both academic and practical fields. This study was carried out first as a theoretical study of the literature, definition and types of facial make up used in the Opera, as a way of examining the formative aspect. Secondly, an analysis was conducted on the main characters, 'Guan Yu' and 'Zhang Fei' of "The Romance of the Three Kingdoms", 'Li Kiu' and 'Lu Zhishen' of "All Men are Brothers" and 'Monkey King' of "Journey to West", employing the collection belonging to 'Yongqi Zhao' who is an expert on the Chinese Beijing Opera. Thirdly, two concepts were categorized, based on the analytic results of the abovementioned characters, each of which were then further categorized into three sub concepts. In regard to cultural development designs, the results of an analysis on the facial make-up color, form, and texture of the four main characters were utilized to construct the themes, "Modern Chic" and "Traditional Splendor". The simplest form that has been represented in the four figures has been applied to "Modern Chic" to show a modern image in which black, white and light blue has been used alongside the vivid red, which is a Chinese favorite, to highlight the characters. In "Traditional Splendor", which is focused on the stage art of the Opera, we see more artistic traditions and colors, to further appeal to our emotions. Traditional motifs have been applied using traditional Chinese arts, in order to develop strong and brilliant colors. The two styles of cultural products were developed in the form of women's scarves and men's ties; a total of 24 designs were expressed, using Illustrator CS6. In the final step, 4 scarves and 6 ties were produced as a sample, using high quality silk. The development of these cultural fashion products will bring an opportunity to show how Chinese traditional culture can be widely utilized in commercial market design.

• Journal of Mushroom
• /
• v.17 no.3
• /
• pp.167-170
• /
• 2019

Cultivation of brown mushrooms, rather than that of white variants is preferred by Korean mushroom farmers, as the former are resistant to diseases. However, brown mushrooms were cultivated only in selective eco-friendly agricultural farms due to lack of consumer awareness. After providing information about brown mushrooms to respondents through a 1-minute video clip, a survey was conducted on social network service (SNS) to assess recognition and preference for brown mushrooms. A food evaluation was then conducted among 200 people randomly selected from the survey respondents. Most respondents (83%) had not encountered brown button mushrooms previously, and 98% of the respondents were willing to buy these mushrooms because they were "curious about its taste" (44%). In the food evaluation, 32% of the respondents found the brown button mushrooms to be delicious, 28% reported a good flavor, and 31% described a good texture. In addition, we confirmed that 95% of respondents were interested in purchasing brown mushrooms after sampling. Therefore, in the present study, we evaluated public perception, preference, and taste of brown button mushrooms, and confirmed that availability of information on nutrition and benefits s of mushroom consumption could induce consumers to buy brown button mushrooms.

• Journal of the Korea Convergence Society
• /
• v.10 no.5
• /
• pp.1-8
• /
• 2019

In this paper, we propose an improved facial skin color extraction method to solve the problem that facial surface is lost due to shadow or illumination in skin color extraction process and skin color extraction is not possible. In the conventional HSV method, when facial surface is brightly illuminated by light, the skin color component is lost in the skin color extraction process, so that a loss area appears on the face surface. In order to solve these problems, we extract the skin color, determine the elements in the H channel value range of the skin color in the HSV color space among the lost skin elements, and combine the coordinates of the lost part with the coordinates of the original image, To minimize the number of In the face detection process, the face was detected using the LBP Cascade Classifier, which represents texture feature information in the extracted skin color image. Experimental results show that the proposed method improves the detection rate and accuracy by 5.8% and 9.6%, respectively, compared with conventional RGB and HSV skin color extraction and face detection using the LBP cascade classifier method.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Food Science and Preservation
• /
• v.16 no.6
• /
• pp.900-907
• /
• 2009

Chiffon cakes were prepared using various concentrations of aloe gel to develop functional baking procedures. The quality characteristics of chiffon cakes prepared after addition of 20%, 40%, or 60% (w/w) aloe gel, substituting for the same levels of wheat flour, were investigated. No significant weight difference between cakes was observed. The height of cakes containing aloe gel was significantly greater than that of control cakes. The baking loss rate (BLR) of aloe gel decreased as the amount of gel increased, and cakes prepared using 60% (w/w) aloe gel had the lowest BLR. Moisture contents of cakes prepared using aloe gel were higher than that of control cakes. Cakes with 60% (w/w) aloe gel had the highest moisture content. The pore size of cakes with 60% (w/w) aloe gel was the smallest of all groups. Crumb color became whiter as the proportion of aloe gel increased. Lightness (L value) of control cake was lower than that of cake containing aloe gel. Redness (a value) of aloe chiffon cakes increased as the proportion of aloe gel rose. Yellowness (b value) of cakes with 40% (w/w) aloe gel was significantly higher than that of the control group. Other cakes showed no difference in b value compared with control cake. Hardness in all cakes prepared with aloe gel was significantly lower than that of the control group. Adhesiveness of control cake was significantly lower than that of other cakes. No significant between-group difference in springiness was observed. The cohesiveness of cakes with 40% (w/w) aloe gel was significantly lower than that of the control group and that of cakes with 20% (w/w) aloe gel. The gumminess and chewiness of control cakes were significantly higher than those of other cakes. The yellowness of cake with 60% (w/w) aloe gel was significantly lower than that of the other groups. Pore size decreased after the addition of aloe gel. There was no significant difference in appearance among cakes thus, all cakes were acceptable to potential consumers. Although no perceptible difference in aloe odor was evident, cakes with 60% (w/w) aloe gel scored significantly lower in flavor acceptance compared with other cakes. No significant between-cake difference in taste acceptance, perceived moisture level, or texture acceptability was observed. Cakes with 40% and 60% (both w/w) aloe gel were of significantly higher density than other cakes. Overall, the acceptability of cakes with 60% (w/w) aloe gel was lower than that of other cakes. Ultimately, the results indicated that quality can be enhanced by adding less than 40% (w/w) aloe gel to chiffon cakes as a substitute for wheat flour.

• Korean Journal of Soil Science and Fertilizer
• /
• v.32 no.2
• /
• pp.123-131
• /
• 1999

To get the basic information for the improvement of the optimum levels of upland soil fertility and fertilizer application, the soil samples in two hundred fifteen site were collected from the major condiment vegetable cultivation areas such as red pepper, garlic and onion fields. Physico-chemical properties of the soil samples were investigated. Soil texture distribution of soil samples in red pepper, garlic and onion cultivation areas was in order of loam (L), sandy loam (SL), silt loam (SiL) and clay loam (CL) (35.4, 31.6, 14.9 and 7.0%, respectively). The average pH of soil in garlic and onion cultivation areas were over pH 6.0, whereas in red pepper was under pH 5.5. The frequency distribution of soil pH in total sampling sites were 58.7% in under pH 6.0 and 21.4% in below pH 5.0, in contrast to 10.3% in over pH 7.0. The organic matter contents were in the range of $20{\sim}30g\;kg^{-1}$, and the onion field soils was a little higher than those in red pepper or garlic. The available phosphate contents were in the range of $719{\sim}746mg\;kg^{-1}$ and were not different among in red pepper, garlic and onion. The frequency distribution of available phosphate in total sampling sites were found 62.8% of above $600mg\;kg^{-1}$, which was over the standard level for upland soil improvement, and then 22.3% was exceeded $1,000mg\;kg^{-1}$, especially. In the exchangeable cations, the K and Ca contents in garlic (1.27 and $9.11cmol\;kg^{-1}$) and onion (1.20 and $8.39cmol\;kg^{-1}$) were higher than in red pepper (0.96 and $5.87cmol\;kg^{-1}$), respectively. The Mg contents in garlic field soils ($2.17cmol\;kg^{-1}$) were higher than those in red pepper and onion (1.51 and $1.80cmol\;kg^{-1}$). This exchangeable K, Ca and Mg contents were higher than the standard level for upland soil improvement. The contents of microelement were ranged in $54.3{\sim}60.1mg\;kg^{-1}$ for Fe, $31.3{\sim}42.3mg\;kg^{-1}$ for Mn, $1.7{\sim}2.3mg\;kg^{-1}$ for Cu and $4.8{\sim}5.5mg\;kg^{-1}$ for Zn, respectively.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.42 no.7
• /
• pp.1103-1108
• /
• 2013

This study was conducted in order to determine the effect of autoclave and microwave treatments on cookies. Wheat dough was treated in an autoclave (30 min), a microwave (1 min), and both autoclave and microwave (30 min/1 min). The treated dough was baked or non-baked and cookies quality was assessed. The pH, moisture content, color, and texture were measured, and sensory evaluation was performed. The pH showed a slight increase when dough was treated in a microwave (before baking) and decreased in both the autoclave and autoclave/microwave (after baking) treatments. The moisture content showed a significant increase, compared to the control, in autoclave treatments. Regarding surface color of cookies, lightness was decreased in all treatments and redness was higher compared with the control, except for microwave (before baking), and yellowness was lower compared to the control, except for microwave treatment (after baking). Hardness, gumminess, chewiness, and shear force showed a significant increase when dough was treated in an autoclave/microwave (after baking) compared to the control. In the sensory evaluation, color, taste, texture, shape, and overall preference of cookies treated with an autoclave/microwave (after baking) showed a low score. These results suggest that autoclaving and microwaving may reduce the quality of bread and that preparation of countermeasures is necessary.

• Korean Journal of Soil Science and Fertilizer
• /
• v.12 no.1
• /
• pp.15-23
• /
• 1979

In the first paper of the series the five soil fertility factors were evaluated by means of principal component analysis and varimax method. They are interpreted as representing, 1) skeletal available phosporus status, 2) organnic matter status, 3) salt status 4) base status, and 5) free oxide status. In order to resynthesize such fragmented information for the overall soil fertility evaluation, the method of multiple regression analysis was adopted, using the five factor scores and yield data for Korean paddy soils as independent and dependent variables respectively. As test of linear models with different combinations of independent variables the results of t-test of regression coefficient were revealed that the organic matter status (FII) has no relevance to the yield of paddy and that the free oxides and salt supply has by it self only an insignificant contribution to the yield. The multiple correlation coefficient (R) revealed its multiple regression analysis was as low as 0.43. Introduction of quadratic terms to the linear model bettered the result. Thus multiple correlation coefficient (R) was increased as 0.59. Therefore, a coefficient of determination 0.35 was obtained by a quadratic model with interaction terms among the five fertility constituents. Generally we think that the fertility factor has more contribution to raise the rice yield in paddy and that the failure of yield prediction by fertility factor scores was caused by one of follows; 1) the roughness of the yield inspection, and 2) missextraction of fertility constituents. The second step in this study, assuming that the residuals by multiple regression analysis were due to factors other than soil fertility, we can now proceed to predicting the yield from the field characters with the classified fertility groups by means of Hayashi's theory of quantification No. 1. Such variables as fertility groups (FTYG), water availability (WATER), soil drainage (DRNG), climatic zone (CLIZ), surface soil's stickiness (STCKT), surface soil's dry consistence (DCNST), and surface soil's texture (FTEXT) are taken up as the explanatory variables. The quantification appears reasonable; the well to extremely well in soil drainage, very sticky of surface soil, inefficiency in water availability, coarse texture, and very hard to extremely hard dry consistence in soil are detrimental to the rice yield. The R was as high as 0.90 for the set of variables. But the given explanatory variables in this study were not quite effective in explaining rice yield. The method developed seems to be promising only if properly collected data are available. Conditions that should be satisfied in the yield inspection obtained from common cultivator for the purpose of deriving a prediction equation were put forward.