• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1989년도 춘계학술대회
• /
• pp.23-26
• /
• 1989

This paper describes the automatic recognition technique for heart enlargement diagnosis with the chest X-ray films enhanced by digital image processing. The technique measures a maximum transverse of the daiphragm and a maximum transverse of the heart by means of direction signature algorithms, then calculates the desired ratio of these two measured values. This is often refered to a cadiothoracic ratio which gives as useful clue for heart enlargement symptom. The experiment results in this paper show presented method is more efficient than the manual diagnosis method of the symptom.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권11호
• /
• pp.4534-4555
• /
• 2015

We propose a robust object cataloging method using multiple locally distinct heterogeneous features for aiding image retrieval. Due to challenges such as variations in object size, orientation, illumination etc. object recognition is extraordinarily challenging problem. In these circumstances, we adapt local interest point detection method which locates prototypical local components in object imageries. In each local component, we exploit heterogeneous features such as gradient-weighted orientation histogram, sum of wavelet responses, histograms using different color spaces etc. and combine these features together to describe each component divergently. A global signature is formed by adapting the concept of bag of feature model which counts frequencies of its local components with respect to words in a dictionary. The proposed method demonstrates its excellence in classifying objects in various complex backgrounds. Our proposed local feature shows classification accuracy of 98% while SURF,SIFT, BRISK and FREAK get 81%, 88%, 84% and 87% respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.2919-2937
• /
• 2020

Post-Quantum Cryptography (PQC) is rapidly developing as a stable and reliable quantum-resistant form of cryptography, throughout the industry. Similarly to existing cryptography, however, it does not prevent a third-party from using the secret key when third party obtains the secret key by deception, unauthorized sharing, or unauthorized proxying. The most effective alternative to preventing such illegal use is the utilization of biometrics during the generation of the secret key. In this paper, we propose a biometric-based secret key generation scheme for multivariate quadratic signature schemes, such as Rainbow. This prevents the secret key from being used by an unauthorized third party through biometric recognition. It also generates a shorter secret key by applying Principal Component Analysis (PCA)-based Confidence Interval Analysis (CIA) as a feature extraction method. This scheme's optimized implementation performed well at high speeds.

• Journal of Information Processing Systems
• /
• 제10권4호
• /
• pp.555-567
• /
• 2014

Biometric performance improvement is a challenging task. In this paper, a hierarchical strategy fusion based on multimodal biometric system is presented. This strategy relies on a combination of several biometric traits using a multi-level biometric fusion hierarchy. The multi-level biometric fusion includes a pre-classification fusion with optimal feature selection and a post-classification fusion that is based on the similarity of the maximum of matching scores. The proposed solution enhances biometric recognition performances based on suitable feature selection and reduction, such as principal component analysis (PCA) and linear discriminant analysis (LDA), as much as not all of the feature vectors components support the performance improvement degree.

• 한국산학기술학회논문지
• /
• 제20권6호
• /
• pp.1-8
• /
• 2019

의료정보는 환자에게 중요한 개인정보로써 반드시 보호되어야 하는 중요 정보이다. EMR((Electronic Medical Records) 시스템은 개인정보와 의료정보가 유출될 경우, 환자의 사생활 침해 등 매우 심각한 피해를 초래할 수 있어 EMR 시스템의 의료정보는 사용자 접근에 관한 제어 및 통제 강화 등 높은 보안성이 요구되는 시스템이다. 특히 의료인이 전자의무기록에 접근할 때, 보안이 강화된 신원확인에 대한 인증방식이 반드시 필요하다. 그러나 기존의 공인인증서 기반의 인증모델은 개인키 관리, 권한위임 등의 문제로 인해 전자의무기록의 보안 특성을 반영하지 못하였다. 본 연구에서는 기존의 전자의무기록(EMR) 시스템 접근 시 문제점을 해결할 수 있는 보안이 강화된 지문인식 기반 인증 모델을 제안한다. 제안한 인증 모델은 PEMS(Private-key Escrow Management Server)를 이용한 EMR 지문인증 모델로서, 개인키 위탁 프로토콜과 개인키 인출 프로토콜을 적용하여, 개인키 관리와 권한위임 문제를 해결할 수 있도록 하였다. 제안한 인증 모델은 성능 실험을 통해 기존의 공인인증서 기반 인증에 비해 수행시간 단축된 것을 확인할 수 있었고, 기존 전자서명 비밀번호 방식을 대체 가능하며, 사용자의 편의성이 증가된 장점이 있다.

• 한국의류산업학회지
• /
• 제15권1호
• /
• pp.103-115
• /
• 2013

This study identifies how the luxury brand marketing mix affects customer equity drivers and suggests intangible equity management strategies so that companies can make long-term profits through luxury brands based on empirical studies of Korean luxury consumers. The results of the study are as follows: First, this study classified the properties that use 8 key factors (product integrity, heritage, exclusivity, premium image, environment and consumption experience, premium price, luxury communication strategy, and brand signature). Second, it shows that product integrity and luxury communication strategy have a positive effect on all customer equity drivers, that brand signature has a positive effect on value equity and brand equity, and that premium price has a negative effect on relation equity. It is important to provide products and services equipped with high quality and luxurious designs based on excellent craftsmanship in order to establish brand equity and value equity. Brand identity needs to be maintained and unique brand signatures need to be developed based on the long history of luxury brands against a traditional backdrop. A diversified communication strategy improves brand recognition while playing a part in facilitating brand association and brand image. In order to improve relationship equity, actions such as a loyalty program to strengthen brand loyalty, need to be taken as well as measures to maintain and enhance customer trust through a reasonable price strategy.

• 지능정보연구
• /
• 제11권1호
• /
• pp.1-15
• /
• 2005

어떤 조직에서 사용자 접근이나 e-Commerce 또는 다른 보안 응용에서 사용하기 위해 보안이 뛰어난 인증 방법을 찾을 때 생체인식시스템이 최근에 보다 많은 주목을 받고 있다. 생체인식시스템은 개인 인식에서 전통적인 방법보다 뛰어난 보안성과 편리성을 제공한다. 생체인식시스템은 어떤 응용 분야에서는 기존의 기술을 대체하거나 보조하고, 다른 응용 분야에서는 사용할 수 있는 유일한 접근방법이 되고 있다. 본 논문에서는 지문, 손 모양, 얼굴, 귀, 홍채, 서명과 필적을 포함한 여러 생체인식 방법들을 조사하고 비교하였다. 이들 방법들은 특정 응용 분야에서 매우 적합하다. 본 논문에서는 특정 응용 분야에 적합한 생체 인식 방법들을 찾아서 분류하였으며, 어떤 방법은 다른 방법에 비해 침입하기가 어려운 것으로 나타났다.

• 무역상무연구
• /
• 제34권
• /
• pp.157-185
• /
• 2007

The purpose of this thesis is to contribute to the activation of e-contract service for one stop e-trade by analyzing the problems and its solutions in e-contract service at home and abroad. In order to achieve the purpose of this thesis, case studies are done on e-contract service providers such as CECTRUST service of NTT DATA in Japan and HanCM.com of Haansoft in Korea and user companies such as Taisei Corporation using CECTRUST service and Hyundai Card using HanCM.com. The problems in the e-contract service are the lack of e-contract service providers, rare publicity of e-contract service, limited use of e-contract service at only home, higher pricing for e-contract service, short time management of e-contract documents by service providers, no application of newly developed security technology to e-contract service, unsatisfaction of requirements of e-contract service provider as trusted third party, absence of lower pricing e-contract service by service provider, authorizing key error in electronic signature under recognized authentication system in case of fail in renewal of digital certificate and reproduction of digital certificate. The solutions of these problems are the upbringing of e-contract service providers, broad publicity of e-contract service, development of e-contract service on a global basis, establishment of lower pricing for e-contract service, long time management of e-contract documents by service providers, application of newly developed security technology such as bio technology to e-contract service, satisfaction of requirements of e-contract service provider as trusted third party by designation of recognized e-document repository, development of lower e-contract service by way of application service provider(ASP), introduction of time stamping of e-contract document and signature key value. The limitation of this thesis is that the problems and its solutions could not meet with the broad recognition as they are conferred by intuition because of few e-contract service provider.

• The Korean Journal of Pain
• /
• 제29권4호
• /
• pp.217-228
• /
• 2016

The musculoskeletal system is mainly composed of the bones, muscles, tendons, and ligaments, in addition to nerves and blood vessels. The greatest difficulty in an ultrasonographic freeze-frame created by the examiner is recognition of the targeted structures without indicators, since an elephant's trunk may not be easily distinguished from its leg. It is not difficult to find descriptive ultrasonographic terms used for educational purposes, which help in distinguishing features of these structures either in a normal or abnormal anatomic condition. However, the terms sometimes create confusion when describing common objects, for example, in Western countries, pears have a triangular shape, but in Asia they are round. Skilled experts in musculoskeletal ultrasound have tried to express certain distinguishing features of anatomic landmarks using terms taken from everyday objects which may be reminiscent of that particular feature. This pictorial review introduces known signature patterns of distinguishing features in musculoskeletal ultrasound in a normal or abnormal condition, and may stir the beginners' interest to play a treasure-hunt game among unfamiliar images within a boundless ocean.

• 비파괴검사학회지
• /
• 제17권4호
• /
• pp.248-261
• /
• 1997

용접 결함에 대한 초음파탐상시험으로부터 결함의 종류를 결정하는 것은 초음파형상인식기법에 의해 가장 잘 해결할 수 있기 때문에 지금까지 이 기법에 대한 연구가 많이 수행되어 왔다. 그러나 이 기법은 지금까지의 많은 연구에도 불구하고, 실제 산업 현장에서는 아직까지 널리 사용되지 못하고 있는 실정이다. 이러한 문제를 해결하기 위해 본 연구에서는, 용접 결함으로부터 초음파 신호를 채취하여 입력하면 적절한 신호처리를 통해 신호의 특징을 추출하고 신경회로망 등 다양한 인공지능기법을 적용하여 용접 결함의 종류를 자동적으로 판별하는 지능형 초음파 신호 분류 소프트웨어를 개발하였다. 그리고 개발된 분류기를 이용하여 용접부내에 존재하는 용접 결함을 균열(Crack)과 비균열(non-crack)으로 분류하는 문제에 적용함으로써, 산업 현장에서 쉽게 이용할 수 있는 실제적인 분류기로서의 가능성을 검증하였다.