• 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 Korea Multimedia Society
• /
• v.20 no.3
• /
• pp.571-580
• /
• 2017

Recently, there are many communication softwares based on text on various smart devices. Unlike traditional print publishing, mobile publishing and SNS tools tends to utilize more decorative or more emotional fonts so that users can pass some feelings from contents. So font providers have released new fonts which deal with the requirements of the market. Nevertheless being released lots of new fonts, general users have not used them because they searched only by font name or font provider's name. It means that there is no way for users to know and find new things. In this study, we suggest font shape classification rules for font registration system based on font design features. We proved the validity of classification standard study through some experiments with 50 commercial fonts. Also the result of this study was provided for Korea Telecommunication Technology Association and adopted by the Korea industrial standard.

• The Journal of the Korea Contents Association
• /
• v.9 no.1
• /
• pp.131-138
• /
• 2009

This paper is about adult certification on Mobile RFID Service Environments coming through the combination of RFID(Radio Frequency IDentification) technology, as the core technology of ubiquitous environments, and mobile telecommunication technology. To overcome the shortcoming of simple adult certification on current internet, we suggest a framework for content-based classification and propose an adult certification system using it. At first, we explain conventional methods for adult certification, and show a criteria of content-based classification for preventing an exposure of adult contents from minors. Additionally, we describe data structure and system for the proposed adult certification on mobile RFID environment, and finish it with concluding remarks.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.06a
• /
• pp.291-292
• /
• 2014

• Review of Korea Contents Association
• /
• v.11 no.3
• /
• pp.48-55
• /
• 2013

• Journal of the Korean Institute of Intelligent Systems
• /
• v.1 no.3
• /
• pp.20-32
• /
• 1991

This study seeks a way a way of dealing with unformatted natural language considering fuzzy set theory. The goal of the study is to establish a framework of an effective language understanding system that is linked to language classification system This study has found that languate understanding is strongly influenced by the language classification. The understanding of language. This study shows that the precision of language classification depends upon the way of how the language is classified in advance. In this study, a fuzzy logic was used to improve the precision of language classification. It was considered that the fuzzy logic might be albe to distinctively classify nuatural language texts into pretinent homogenious groups where contents of the language were identical. Accordingly, in the study, it was expected that classification of language were precisely classified by the fuzzy logic. An experimentalsystems was designed to evaluate the performane of a natural language understanding system that was connected to a fuzzy language classification system. Finally, the experiment suggests that a successful language understanding should require an real time interaction between mem andmachine fuzzy provious language classification.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.66-71
• /
• 2005

Using for the internet information is easy or difficult. The effort to obtain the useful information is developed the various technique such as search as well as the information repository, classification, processing and the utilization. Specially, such developments are remarkable to the Agent of various uses and the classification, conversion in processing techniques. The study introduces the classification service system of internet documents which is processing from the repository of internet information to the automatic classification and search service.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.05a
• /
• pp.84-87
• /
• 2006

It was investigated what is the reasonable landcover classification system for the nonpoint pollution models. According to the parameters of the nonpoint pollution models, runoff curve number, crop management factor and Manning's roughness coefficient, the landcover classification system was proposed to manage the drainage basin of the Woopo wetland. Also, the rule-based classification method was adopted to extract the landcover information for this study area.

• Journal of Digital Contents Society
• /
• v.5 no.3
• /
• pp.234-238
• /
• 2004

The system facilities in mobile communications networks are mainly classified into the coverage and usage in the viewpoint of the investments requirements. Based on the classification criterion, the interconnection charging between the wired operators art wireless operators is determined. In this paper, to decide the scale of the interconnection charging a new classification method is proposed by using the system capacity(Erlang, throughput) and subscriber`s estimated demand. The coverage ratio is first evaluated for each facility, and then more efficient interconnection charging model will be presented.

• ETRI Journal
• /
• v.37 no.4
• /
• pp.813-823
• /
• 2015

Because protein is a primary element responsible for biological or biochemical roles in living bodies, protein function is the core and basis information for biomedical studies. However, recent advances in bio technologies have created an explosive increase in the amount of published literature; therefore, biomedical researchers have a hard time finding needed protein function information. In this paper, a classification system for biomedical literature providing protein function evidence is proposed. Note that, despite our best efforts, we have been unable to find previous studies on the proposed issue. To classify papers based on protein function evidence, we should consider whether the main claim of a paper is to assert a protein function. We, therefore, propose two novel features - protein and assertion. Our experimental results show a classification performance with 71.89% precision, 90.0% recall, and a 79.94% F-measure. In addition, to verify the usefulness of the proposed classification system, two case study applications are investigated - information retrieval for protein function and automatic summarization for protein function text. It is shown that the proposed classification system can be successfully applied to these applications.