• Journal of the Korean Wood Science and Technology
• /
• v.45 no.6
• /
• pp.797-808
• /
• 2017

Automatic wood species identification systems have enabled fast and accurate identification of wood species outside of specialized laboratories with well-trained experts on wood species identification. Conventional automatic wood species identification systems consist of two major parts: a feature extractor and a classifier. Feature extractors require hand-engineering to obtain optimal features to quantify the content of an image. A Convolutional Neural Network (CNN), which is one of the Deep Learning methods, trained for wood species can extract intrinsic feature representations and classify them correctly. It usually outperforms classifiers built on top of extracted features with a hand-tuning process. We developed an automatic wood species identification system utilizing CNN models such as LeNet, MiniVGGNet, and their variants. A smartphone camera was used for obtaining macroscopic images of rough sawn surfaces from cross sections of woods. Five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch) were under classification by the CNN models. The highest and most stable CNN model was LeNet3 that is two additional layers added to the original LeNet architecture. The accuracy of species identification by LeNet3 architecture for the five Korean softwood species was 99.3%. The result showed the automatic wood species identification system is sufficiently fast and accurate as well as small to be deployed to a mobile device such as a smartphone.

• Journal of KIISE:Databases
• /
• v.41 no.4
• /
• pp.199-208
• /
• 2014

In this paper, we represent a system of identification and feature search for scanned comics in consideration of their content characteristics. For creating the feature of the scanned comics, we utilize a method of hierarchical symmetry fingerprinting. Proposed identification and search system is designed to give online service provider, such as Webhard, an immediate identification result under conditions of huge volume of the scanned comics. In simulation part, we analyze the robustness of the identification of the fingerprint to image modification such as rotation and translation. Also, we represent a structure of database for fast matching in feature point database, and compare search performance between other existing searching methods such as full-search and most significant feature search.

• Fire Science and Engineering
• /
• v.24 no.3
• /
• pp.78-85
• /
• 2010

Currently, there are various institutions performing fire investigation and identification, such as fire stations and police stations as well as institutes related to fire safety, etc. And the manpower working at the institutions reaches a large number of persons. But there is no objective index on the expertise of the persons. In this paper, we suggested the examination criteria through job analysis and the enforcement method of the exam system. And we developed suitable exam subjects and exam content specifications for qualification of fire identification and estimation that investigate a fire cause, combustion, escape circumstances and fire facilities at the scene of a fire, survey the fire damage and analysis fire cause, etc. It will increase the public trust to develop national technical qualification items of the fire identification and estimation engineer.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.352-359
• /
• 2021

The purpose of this study is to design and build fake news discrimination systems and methods using fact-checking guidelines. In other words, the main content of this study is the system for identifying fake news using Artificial Intelligence -based Fact-checking guidelines. Specifically planned guidelines are needed to determine fake news that is prevalent these days, and the purpose of these guidelines is fact-checking. Identifying fake news immediately after seeing a huge amount of news is inefficient in handling and ineffective in handling. For this reason, we would like to design a fake news identification system using the fact-checking guidelines to create guidelines based on pattern analysis against fake news and real news data. The model will monitor the fact-checking guideline model modeled to determine the Fact-checking target within the news article and news articles shared on social networking service sites. Through this, the model is reflected in the fact-checking guideline model by analyzing news monitoring devices that select suspicious news articles based on their user responses. The core of this research model is a fake news identification device that determines the authenticity of this suspected news article. So, we propose news article identification methods with fact-checking guideline on Artificial Intelligence & Bigdata. This study will help news subscribers determine news that is unclear in its authenticity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3149-3165
• /
• 2013

Content based image retrieval is increasingly gaining popularity among image repository systems as images are a big source of digital communication and information sharing. Identification of image content is done through feature extraction which is the key operation for a successful content based image retrieval system. In this paper content based image retrieval system has been developed by adopting a strategy of combining multiple features of shape, color and relevance feedback. Shape is served as a primary operation to identify images whereas color and relevance feedback have been used as supporting features to make the system more efficient and accurate. Shape features are estimated through second derivative, least square polynomial and shapes coding methods. Color is estimated through max-min mean of neighborhood intensities. A new technique has been introduced for relevance feedback without bothering the user.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.49 no.5
• /
• pp.423-428
• /
• 2004

Soybean seeds contain high amounts of isoflavones that display biological effects and isoflavone content of soybean seed can vary by year, environment, and genotype. Objective of this study was to identify quantitative trait loci that underlie isoflavone content in soybean seeds. The study involved 85 $F_2$ populations derived from Korean soybean cultivar 'Kwangkyo' and wild type soybean 'IT182305' for QTL analysis associated with isoflavone content. Isoflavone content of seeds was determined by HPLC. The genetic map of 33 linkage groups with 207 markers was constructed. The linkage map spanned 2,607.5 cM across all 33 linkage groups. The average linkage distance between pair of markers among all linkage groups was 12.6 cM in Kosambi map units. Isoflavone content in $F_2$ generations varied in a fashion that suggested a continuous, polygenic inheritance. Eleven markers (4 RAPD, 3 SSR, 4 AFLP) were significantly associated with isoflavone content. Only two markers, Satt419 and CTCGAG3 had F-tests that were significant at P<0.01 in $F_2$ generation for isoflavone content. Interval mapping using the $F_2$ data revealed only two putative QTLs for isoflavone content. The peak QTL region on linkage group 3, which was near OPAG03c, explained $14\%$ variation for isoflavone content. The peak QTL region on linkage group 5, which was located near OPN14 accounted for $35.3\%$ variation for isoflavone content. Using both Map-Maker-QTL $(LOD{\geq}2.0)$ and single-factor analysis $(P{\leq}0.05)$, one marker, CTCGAG3 in linkage group 3 was associated with QTLs for isoflavone content. This information would then be used in identification of QTLs for isoflavone content with precision

• Journal of Ginseng Research
• /
• v.14 no.2
• /
• pp.112-116
• /
• 1990

As a part of studies on the quality control of crude drug preparation drinks, ginseng saponins were identified by HPLC. Ginsenoside-Rb1 was determined quantitatively by HPLC. Ginsenoside MeOH/H2O(65:35:10, v/v) on Si-gel plate. Ginsenoside-Rb1 content determined by HPLC on Lichrosorbtract drinks was 57.5-70.4% compared to the content in the red ginseng extract.

• Fashion & Textile Research Journal
• /
• v.16 no.5
• /
• pp.756-765
• /
• 2014

Customer-company (C-C) identification is the perceived fit between the identities of a consumer and an organization. If a consumer identifies with a company that places a high priority on being socially responsible, a consumer who also values social responsibility may support and patronize that business because of the link between something that is important to both them and the company. Because C-C identification may explain the success of cause-related marketing (CRM) in the fashion industry, we investigated the effect of an image resulting from CRM on ratings of brand attributes (e.g., distinctiveness, credibility, attractiveness), identification with the brand, attitude toward the brand, and customer loyalty. Participants also responded to open-ended questions reflecting their rationale for their ratings of brand attributes. Data were collected from a convenience sample of undergraduates (n = 228) enrolled at Midwestern University in the U.S. Structural equation modeling revealed that as ratings of the social responsibility of the cause-related marketing effort increased so did perceptions of the brand's distinctiveness, credibility, and attractiveness. Participants identified with a brand when they rated the brand as attractive. Participants' identification with a brand had a significant impact on attitudes toward the brand and customer loyalty (e.g., purchase intention, willingness to spread positive word-of-mouth). Content analyses of open-ended responses supported the idea that brand images stemming from CRM exert an important influence on consumer's ratings of brand attributes. Fashion marketers interested in cause-related marketing will find success with efforts that increase customer identification.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.4
• /
• pp.163-168
• /
• 2005

In this paper, we propose a character-based summarization algorithm using speaker identification method from the dialog in video. First, we extract the dialog of shots containing characters' face and then, classify the scene according to actor/actress by performing speaker identification. The classifier is based on the GMM(Gaussian Mixture Model) using the 24 values of MFCC(Mel Frequency Cepstrum Coefficient). GMM is trained to recognize one actor/actress among four who are all trained by GMM. Our experiment result shows that GMM classifier obtains the error rate of 0.138 from our video data.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.3
• /
• pp.210-215
• /
• 2014

In spite of distortion caused by noise and echo, the audio fingerprinting technique must identify successfully an audio source. This audio fingerprinting technique is applying for TV commercial advertisement identification. In this paper, we propose a robust audio fingerprinting method for TV commercial advertisement identification. In the proposed method, a prominent audio peak pair fingerprint based on constant Q transform improves the accuracy of the audio fingerprinting system in real noisy environments. Experimental results confirm that the proposed method is quite robust than previous audio fingerprinting method in different noise conditions and achieves promising accurate results.