• Journal of the Korea Society of Computer and Information
• /
• v.20 no.12
• /
• pp.21-28
• /
• 2015

In this paper, we propose a method of glasses detection in facial image. we develop a detection method of glasses with a weighted sum of the results that detected by facial element detection and glasses frame candidate region. Component of the face detection method detects the glasses, by defining the detection probability of the glasses according to the detection of a face component. Method using the candidate region of the glasses frame detects the glasses, by defining feature of the glasses frame in the candidate region. finally, The results of the combined weight of both methods are obtained. The proposed method in this paper is expected to increase security system's recognition on facial accessories by raising detection performance of glasses or sunglasses for using ATM.

• Journal of KIISE:Software and Applications
• /
• v.26 no.3
• /
• pp.380-392
• /
• 1999

객체지향 분석과정중에 오류를 검출하고 일관성을 점검하여 무결성을 유지하는 것은 중요한 일이다. 그러나, 현재의 객체지향 개발 방법론은 객체지향 분석모델들에 대하여 오류 검출과 일관성 점검을 위한 정형화된 방법을 제시하지 못하고 있다. 본 논문은 지식베이스를 이용하여 , 객체지향 분석모델들에 대한 오류와 일관성 검증방법을 제안한다. 제안한 방법은 모형화 단계, 정형화 단계, 검증 단계의 세단계로 이루어져 있다. 모형화 단계에서는 시스템을 분석하여 OMT(Object Modeling Technique)방법론의 세 가지 모델인 객체모델, 동적 모델, 기능모델을 생성한다. 이 단계는 OMT의 분석단계에 해당한다. 정형화 단계에서는 이 세가지 모델들을 Atomic Formula 형태로 정형 명세하여 응용 지식베이스에 저장한다. 검증 단계에서는 오류 검출 규칙과 일관성 점검 규칙을 이용하여 오류를 점검하고 일관성을 유지한다. 그리고 본 논문에서 제안한 점검 방법을 적용하여 ATM(Automated Teller Machine)예제의 분석결과를 검증했다. 제안한 방법을 이용하면 보다 더 신뢰할 수 있는 분석모델을 얻을 수 있을 것으로 기대된다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.4
• /
• pp.731-742
• /
• 2017

For all the various cryptographic techniques related to security, social technological attacks such as a shoulder surfing are infeasible to block off completely. Especially, the attacks are executed against financial facilities such as automated teller machine(ATM) which are located in public areas. Furthermore, online financial services whose rate of task management is consistently increasing are vulnerable to a shoulder surfing, smudge attacks, and key stroke inference attacks with google glass behind the convenience of ubiquitous business transactions. In this paper, we show that the security of ATM and internet banking can be reinforced against a shoulder surfing by using One-Time Keypad(OTK) and compare the security of OTK with those of ordinary keypad and One-Time Password(OTP).

• The KIPS Transactions:PartD
• /
• v.17D no.2
• /
• pp.167-174
• /
• 2010

When entering the PIN(personal identification number), the greatest security threat is shoulder surfing attack. Shoulder surfing attack is watching the PIN being entered from over the shoulder to obtain the number, and it is the most common and at the same time the most powerful security threat of stealing the PIN. In this paper, a psychology based PINpad technology referred to as DAS(Dynamic Authentication System) that safeguards from shoulder surfing attack was proposed. Also, safety of the proposed DAS from shoulder surfing attack was tested and verified through intuitive viewpoint, shoulder surfing test, and theoretical analysis. Then, a PINpad with an internal DAS that was certified for its safety from shoulder surfing attack was designed and produced. Because the designed PINpad significantly decreases the chances for shoulder surfing attackers being able to steal the PIN when compared to the ordinary PINpad, it was determined to be suitable for use at ATM(automated teller machine)s operated by banks and therefore has been introduced and is being used by many financial institutions.