• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1207-1214
• /
• 2019

Technologies of the 4th industrial revolution have been unknowingly seeping into our lives. Many IoT based home security systems are using the convolutional neural network(CNN) as good biometrics to recognize a face and protect home and family from intruders since CNN has demonstrated its excellent ability in image recognition. In this paper, three layouts of CNN for 2D and 2.5D image of small dataset with various input image size and filter size are explored. The simulation results show that the layout of CNN with 50*50 input size of 2.5D image, 2 convolution and max pooling layer, and 3*3 filter size for small dataset of 2.5D image is optimal for a home security system with recognition accuracy of 0.966. In addition, the longest CPU time consumption for one input image is 0.057S. The proposed layout of CNN for a face recognition is suitable to control the actuators in the home security system because a home security system requires good face recognition and short recognition time.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.26 no.4
• /
• pp.22-29
• /
• 2008

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.5
• /
• pp.1007-1017
• /
• 2019

Currently, most biometrics system authenticates users by using single biometric information. This method has many problems such as noise problem, sensitivity to data, spoofing, a limitation of recognition rate. One method to solve this problems is to use multi biometric information. The multi biometric authentication system performs information fusion for each biometric information to generate new information, and then uses the new information to authenticate the user. Among information fusion methods, a score-level fusion method is widely used. However, there is a problem that a normalization operation is required, and even if data is same, the recognition rate varies depending on the normalization method. A rank-level fusion method that does not require normalization is proposed. However, a existing rank-level fusion methods have lower recognition rate than score-level fusion methods. To solve this problem, we propose a rank-level fusion method with higher recognition rate than a score-level fusion method using correlation coefficient. The experiment compares recognition rate of a existing rank-level fusion methods with the recognition rate of proposed method using iris information(CASIA V3) and face information(FERET V1). We also compare with score-level fusion methods. As a result, the recognition rate improve from about 0.3% to 3.3%.

• The KIPS Transactions:PartB
• /
• v.11B no.7 s.96
• /
• pp.759-768
• /
• 2004

Recently the biometric recognition technology is intensively studied and the standardization of the technology has been highly demanded for its commercialization. Currently many blometric recognition products are being developed based on the BioAPl(Biometric Application Program-ming Interface) specification. However, the reliable testing tools (or scenarios) to evaluate performance and conformance of the products are not shown yet. In this paper, a conformance testing method is presented, which verifies a biometric recognition system to meet the requirements of the BioAPl standard. Two different testing procedures are used in the proposed method. The first procedure evaluates that each functions offered in the BioAPl specification are correctly implemented and that the functions are actually used in the system. Through the Procedure, a BSP(Biometric Service Provider) system is executed on the framework of the BioAPl functions. It requires selection of parameters and prece-dent functions that should be executed first. The second procedure evaluates the abilities of module management, handling operations and ver-ification process by the analysis of the test cases. It tests the correctness of the system operation when a testing scenario is given. The proposed testing method is applied on a fingerprint verification BSP using the sample BSP provided by the BioAPl consortium. The experimental results shows the benefits of the proposed testing method.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.667-680
• /
• 2007

The bio-data processing is used for a suitable purpose with bio-signals, which are obtained from human individuals. Recently, there is increasing demand that the bio-data has been widely applied to various applications. However, it is often that the number of data within each class is limited and the number of classes is large due to the property of problem domain. Therefore, the conventional pattern recognition systems and classification methods are suffering form low generalization performance because the system using the lack of data is influenced by noises of that. To solve this problem, we propose a modified additive factor model for bio-data generation, with two factors; the class factor which affects properties of each individuals and the environment factor such as noises which affects all classes. We then develop a classification system through defining a new similarity function using the proposed model. The proposed method maximizes to use an information of the class classification. So, we can expect to obtain good generalization performances with robust noises from small number of datas for bio-data. Experimental results show that proposed method outperforms significantly conventional method with real bio-data.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.925-927
• /
• 2005

홍채 인식(Iris Recognition)은 동공과 흰자위 사이에 있는 홍채의 모양 패턴이 평생 변하지 않고, 사람마다 다른 패턴을 가진다는 특성을 이용하여 개인을 식별하는 기술로, 생체인식(Biometrics) 부분에서는 탁월한 식별력 및 신뢰성을 인정 받고 있다. 상당수의 기존 연구들은 원천 특허를 채택한 상태에서 성능 개선을 연구해 왔기 때문에 원천적인 한계를 가지고 있었다. 본 논문은 웨이블릿(Wavelet) 변환을 이용하여 특징을 추출하는 기존 방식과 다르게 프랙탈(Fractal) 방법으로 압축된 다수의 원 영상에 대해 입력된 영상의 유사도를 측정, 개인을 식별하는 새로운 홍채인식 방법을 제안한다. 이를 통해 타 연구들에서 제안했던 특별한 최적화 알고리즘을 사용하지 않고도 크게 떨어지지 않는 인식률을 얻을 수 있다.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.1100-1102
• /
• 2017

본 연구는 양손이 불편하거나 없는 상지장애인이 도어락의 잠금 해제를 할 수 있도록 화자 인식 기술을 이용한 도어락을 구현하였다. 현재까지 대부분의 도어락 기술은 일반인 대상으로 개발되어 생체인식 기술을 활용하는 단계까지 발전하였으나 기본적으로는 사람이 가장 잘 사용하는 신체 부위인 손을 기준으로 발달되어 손의 활용이 필요한 방식으로 양손이 불편한 상지 장애인의 사용에는 불편함을 주었다. 따라서 본 연구는 도어락 장금 장치에 화자인식 기술을 활용하여 상지 장애인도 이용 가능한 도어락 잠금 패키지를 제안하고, 구현한다. 일반인에서 상지 장애인도 사용할 수 있도록 화자 인식 기술을 이용하여 보다 보편적으로 사용 가능한 도어락 시스템을 설계하는데 기여할 수 있다.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.645-647
• /
• 2018

최근 IoT의 기술의 발달로 사용자 인식에 관한 연구가 주목을 받고 있다. 사용자 인식은 각 사용자만의 특징에 근거하여 특정 사용자를 인식하는 기술이다. 사용자 인식과 관련하여 홍채나 지문인식 등과 같은 생체 인식, 얼굴 인식 그리고 걸음걸이 인식 등에 관한 연구들이 진행되고 있다. 다양한 방식은 각각의 인식률을 높이기 위해 노력하고 있지만, 인식하고자 하는 사용자의 상황에 따라 인식률에 영향을 받게 된다. 본 연구에서는 다양한 방식을 여러 단계로 구성하여 다양한 상황에 놓인 사용자를 인식하기 위한 방법을 연구한다. 제안 시스템은 드론에서 촬영된 영상을 수신하는 것을 기반으로 하여 얼굴인식과 걸음걸이 인식을 이용한 방식이다. 1차적으로 사람의 얼굴을 탐지를 하고, 사람의 얼굴이 탐지되었을 때는 얼굴 인식을 수행한다. 탐지하지 못했을 경우 걸음걸이 인식을 수행하여 인식률을 향상시킨다.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.19 no.7
• /
• pp.60-70
• /
• 2001

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.143-150
• /
• 2006

Recently, the fields such as internet banking and electronic commerce are more and more growing due to the growth of practical use of personal computer and the progress of communication technology, So importance of information security has been increased. In fact, traditional identification systems are inherently insecure because the personal identification information can be forgotten, stolen or lost. In this paper, we propose an identification system that can decide whether the user is registered based on iris information using a mouse. The proposed system is mounted a CCD camera and an illumination device on general type mouse. Then it decides whether the user is registered after the acquired image are processed and analyzed. This system gives a PC user the advantage of low-cost and convenience without necessity preparing high-cost equipment for biometrics when using a identification system.