• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.2
• /
• pp.354-368
• /
• 2020

Accurate and versatile image data-sets are essential for fashion AI research and AI-based fashion businesses based on a systematic attribute classification system. This study constructs a color and texture attribute hierarchical classification system by collecting fashion item images and analyzing the metadata of fashion items described by consumers. Essential dimensions to explain color and texture attributes were extracted; in addition, attribute values for each dimension were constructed based on metadata and previous studies. This hierarchical classification system satisfies consistency, exclusiveness, inclusiveness, and flexibility. The image tagging to confirm the usefulness of the proposed classification system indicated that the contents of attributes of the same image differ depending on the annotator that require a clear standard for distinguishing differences between the properties. This classification system will improve the reliability of the training data for machine learning, by providing standardized criteria for tasks such as tagging and annotating of fashion items.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.16 no.10
• /
• pp.938-945
• /
• 2003

We fabricated Ni-substrate for YBCO coated conductors and evaluated the effects of pressing and annealing temperature and time on texture. Ni substrate was fabricated by powder metallurgy technique and compacts were prepared by applying uniaxial or isostatic pressure. The texture of substrate made by applying cold isostatic pressure (CIP) was stronger than that by uniaxial pressure which we attribute to the fact that the CIP method provided higher density and more uniform density distribution. It was observed that the substrate annealed at 400 C showed both retained texture and recrystallized texture. On the other hand, the texture of substrate significantly improved at annealing temperature above 500 C, forming strong 4-fold symmetry, [111] II ND texture, and FWHM of 9∼10 . It is to be noted that the degree of texture was almost independent of annealing temperature (500∼1000 C) and annealing time(1∼54 min, at 1000 C). EBSD and AFM analysis indicated that 99% of grain boundaries was low angle grain boundary and RMS was approximately 3 nm, respectively. Development of strong cube texture and high fraction of low angle grain boundary of Ni-substrate made by powder metallurgy technique in our study is considered to be suitable for the application of YBCO coated conductors.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.533-538
• /
• 2001

In this paper, we extend FARGs single mode attribute to multiple attributes for real image application and present a new CBIR using FMARG(Fuzzy Multiple Attribute Relational Graph), which can handle queries involving multiple attributes, not only object label, but also color, texture and spatial relation. In the experiment using the synthetic image database of 1,024 images and the natural image database of 1.026 images built from NETRA database and Corel Draw, the proposed approach shows 6~30% recall increase in the synthetic image database and a good performance, at the displacements and the retrieved number of similar images in the natural image database, compared with the single attribute approach.

• Journal of Biosystems Engineering
• /
• v.37 no.5
• /
• pp.319-326
• /
• 2012

Purpose: Cheese texture is an important sensory attribute mainly considered for consumers' acceptance. The feasibility of nondestructive measurements of cheese texture was explored using non-contact ultrasonic sensors. Methods: A novel non-contact air instability compensation ultrasonic technique was used for five varieties of hard cheeses to measure ultrasonic parameters, such as velocity and attenuation coefficient. Five texture properties, such as fracturability, hardness, springiness, cohesiveness, and chewiness were assessed by a texture profile analysis (TPA) and correlated with the ultrasonic parameters. Results: Texture properties of five varieties of hard cheese were estimated using ultrasonic parameters with regression analysis models. The most effective model predicted the fracturability, hardness, springiness, and chewiness, with the determination coefficients of 0.946 (RMSE = 21.82 N), 0.944 (RMSE = 63.46 N), 0.797 (RMSE = 0.06 ratio), and 0.833 (RMSE = 17.49 N), respectively. Conclusions: This study demonstrated that the non-contact air instability compensation ultrasonic sensing technique can be an effective tool for rapid and non-destructive determination of cheese texture.

• Culinary science and hospitality research
• /
• v.23 no.7
• /
• pp.129-139
• /
• 2017

This study investigated the quality characteristics of baked rice cake using dry and wet rice flour. The moisture contents, color values, texture and sensory evaluation(attribute difference and acceptance) for the samples were tested. The moisture content of baked rice cake was the highest in rice cake baked with non- glutinous rice of dry type, and rice cake baked in dry type had weaker brownishness and therefore had higher brightness value compared to the rice cake baked in wet type. In relation to the texture, the hardness was found to be the highest in the rice cake baked with wet non- glutinous rice, and the rice cake baked with glutinous rice was found to be soft. The hardness was the lowest in both wet and dry glutinous rice, and was the highest in the wet non- glutinous rice. Attribute difference test of samples showed that, the rice cake baked with glutinous rice showed clear manifestation of springiness, moistness, adhesiveness, and gumminess (except for the harness). Although the cake baked with dry rice powder showed no significant difference, the dry glutinous rice flour was preferred the most. The rice cake baked with wet glutinous rice flour was preferred the most in terms of flavor, taste, texture, and overall acceptability.

• Culinary science and hospitality research
• /
• v.19 no.5
• /
• pp.184-195
• /
• 2013

The purpose of this study is to develop fresh pasta added with superjami, which had a high C3G (cyanidin-3-glucoside). Making fresh pasta with wheat flour and superjami(0, 10, 20, 30, 40%) was done, followed by the mechanical test(moisture content, color value, weight, volume, texture, tension) and the sensory analysis(attribute difference test, preference test). Results are as follows. Moisture content of fresh pasta and cooked pasta was the highest in SP40, and the scores of cooked pasta was much higher than those of fresh pasta. L, a and b value decreased as the ratio of superjami powder. Hardness, chewiness and tension force decreased, while weight, volume, adhesiveness and tension distance increased as the ratio of superjami powder. Attribute difference test showed that color intensity, superjami flavor, savory flavor, superjami taste, savory taste, graininess and after swallow were intense as superjami powder was added. The preference test showed that SP20 containing 20% of superjami powder was the most preferable in flavor, taste, texture and overall quality. Therefore, this was taken as the optimal superjami powder contents for maximizing the overall quality of fresh pasta.

• Geophysics and Geophysical Exploration
• /
• v.24 no.3
• /
• pp.113-130
• /
• 2021

Recently, ground-penetrating radar (GPR) surveys have been actively employed to obtain a large amount of data on occurrences such as ground subsidence and road safety. However, considering the cost and time efficiency, more intuitive and accurate interpretation methods are required, as interpreting a whole survey data set is a cost-intensive process. For this purpose, GPR data can be subjected to attribute analysis, which allows quantitative interpretation. Among the seismic attributes that have been widely used in the field of exploration, complex trace analysis and similarity are the most suitable methods for analyzing GPR data. Further, recently proposed attributes such as edge detecting and texture attributes are also effective for GPR data analysis because of the advances in image processing. In this paper, as a reference for research on the attribute analysis of GPR data, we introduce the useful attributes for GPR data and describe their concepts. Further, we present an analysis of the interpretation methods based on the attribute analysis and past cases.

• Food Quality and Culture
• /
• v.2 no.1
• /
• pp.27-31
• /
• 2008

The objective of this study was to develop sensory lexicons that can be utilized for various types of tofu such as pressed, unpressed, and tofu made from germinated soybeans, using generic descriptive analysis. In the first phase of the experiment, trained descriptive panelists developed and defined the appearance, aroma, flavor, and texture attributes that are commonly present in tofu. Then, the sensory characteristics of seven types of tofu were analyzed using the sensory lexicons established in the initial stage of the experiment. Four appearance, 6 odor/aroma, 6 flavor/taste, 7 texture, and 4 aftertaste attributes were identified, and reference standards were established for most of the terms in order to facilitate the understanding of the attribute definitions. The intensities of the sensory attributes were measured on a 15-point scale. Statistical analyses, including analysis of variance and principal component analysis, were used for the data. The seven tofu samples showed significant differences in the intensities of 22 attributes. The unpressed tofu samples were generally rated as being high in moistness, easy to cut, silky, and easy to swallow. The pressed tofu, on the other hand, was salty, astringent, beany, hard, and rough in texture. The tofu made with germinated soybeans was characterized as having a strong cooked bean flavor, salty and astringent aftertaste, and hard texture. Overall, the attributes of moistness, easy to swallow, and silkiness showed strong positive correlations; hardness and sticks to teeth were also positively correlated to each other.

• Culinary science and hospitality research
• /
• v.24 no.3
• /
• pp.35-46
• /
• 2018

This study investigated the quality characteristics of makpyeon made of dry milled rice powder according to soaking time. Makpyeon samples made of dry milled rice powder were analyzied with various soacking time, the moisture content, pH, Hunter's color value texture characteristics, attribute difference test and acceptance test. The moisture content of makpyeon did not indicate difference among samples. pH resulted in MS90 showed the lowest moisture content. The L-value (lightness) and a-value (greenness) result in that MS0 showed the highest and decreased according to soaking time. The b-value (yellowness) increased according to soaking time, MS90 showed the highest. TPA resulted in that MS90 indicated the highest hardness, chewiness, gumminess and the lowest adhesiveness. Hardness of makpyeon samples was higher than sulgitteok samples, adhesiveness was lower than those of sulgitteok in each soaking time. Based on attribute difference test, the score of brightness, moistness, glossy, particle size were decreased and firmness were increased according to soaking times. Flavor, taste and mouth feel attribute was stronger in makpyeon samples with the longer soaking time. Acceptance results showed that MS0 and MS30 (soaking for 30 min) were preferred the most. Also limitations and future research directions of this study were discussed.

• Korean Journal of Food Science and Technology
• /
• v.26 no.6
• /
• pp.776-780
• /
• 1994

Fuzzy reasoning was applied to sensory evaluation of cooked rice. A sensory attribute diagnostics was done in terms of tour kinds of attributes-texture, taste, odor and appearance which determine overall palatability. First, rating for the contribution level of each attribute to the overall palatability was asked as one of five scales-very important, important, moderate, slight and very slight. Secondly, the preference level of each attribute for a cooked rice sample was asked as one of five hedonic scales-excellent, good, fair, poor and very poor. Thirdly, the results of the scales were converted into fuzzy values and operated by fuzzy reasoning. Finally, the contribution and preference levels of the attributes were composed to infer the overall palatability of cooked rice sample.