• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2690-2701
• /
• 2013

Humans are able to recognize small number of people they know well by the way they walk. This ability represents basic motivation for using human gait as the means for biometric identification. Such biometric can be captured at public places from a distance without subject's collaboration, awareness or even consent. Although current approaches give encouraging results, we are still far from effective use in practical applications. In general, methods set various constraints to circumvent the influence factors like changes of view, walking speed, capture environment, clothing, footwear, object carrying, that have negative impact on recognition results. In this paper we investigate the influence of walking speed variation to different visual based gait recognition approaches and propose normalization based on geometric transformations, which mitigates its influence on recognition results. With the evaluation on MoBo gait dataset we demonstrate the benefits of using such normalization in combination with different types of gait recognition approaches.

• Journal of Korea Multimedia Society
• /
• v.19 no.5
• /
• pp.881-889
• /
• 2016

Ocular region recently emerged as a new biometric trait for overcoming the limitations of iris recognition performance at the situation that cannot expect high user cooperation, because the acquisition of an ocular image does not require high user cooperation and close capture unlike an iris image. This study proposes a new method for ocular image recognition based on BRISK (binary robust invariant scalable keypoints). It uses the distance ratio of the two nearest neighbors to improve the accuracy of the detection of corresponding keypoint pairs, and it also uses geometric constraint for eliminating incorrect keypoint pairs. Experiments for evaluating the validity the proposed method were performed on MMU public database. The person recognition rate on left and right ocular image datasets showed 91.1% and 90.6% respectively. The performance represents about 5% higher accuracy than the SIFT-based method which has been widely used in a biometric field.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1347-1355
• /
• 2019

Deep learning approach based on convolution neural network (CNN) has extensively studied in the field of computer vision. However, periocular feature extraction using CNN was not well studied because it is practically impossible to collect large volume of biometric data. This study uses the ResNet model which was trained with the ImageNet dataset. To overcome the problem of insufficient training data, we focused on the training of multi-layer perception (MLP) having simple structure rather than training the CNN having complex structure. It first extracts features using the pretrained ResNet model and reduces the feature dimension by principle component analysis (PCA), then trains a MLP classifier. Experimental results with the public periocular dataset UBIPr show that the proposed method is effective in person authentication using periocular region. Especially it has the advantage which can be directly applied for other biometric traits.

• Journal of Information Processing Systems
• /
• v.14 no.2
• /
• pp.435-447
• /
• 2018

Fingerprint-based biometric identification is one of the most interesting automatic systems for identifying individuals. Owing to the poor sensing environment and poor quality of skin, biometrics remains a challenging problem. The main contribution of this paper is to propose a new approach to recognizing a person's fingerprint using the fingerprint's local characteristics. The proposed approach introduces the barycenter notion applied to triangles formed by the Delaunay triangulation once the extraction of minutiae is achieved. This ensures the exact location of similar triangles generated by the Delaunay triangulation in the recognition process. The results of an experiment conducted on a challenging public database (i.e., FVC2004) show significant improvement with regard to fingerprint identification compared to simple Delaunay triangulation, and the obtained results are very encouraging.

• Environmental Analysis Health and Toxicology
• /
• v.4 no.3_4
• /
• pp.61-75
• /
• 1989

Influences of the concurrent administration of carbon tetrachloride and prednisolone on the biometric, biochemical and histological findings were investigated in male rats prefered twice Sosio-Tang extracts at intervals of 24 hours. Influences of the concurrent admininistration of carbon tetrachlorides and prednisolone twice a week respectively on the findings were also investigated in male rats fed freely diet and. tab water mixed with Sosio-Tang extracts for six weeks. 1. Sosio-Tang extracts. decreased the toxicity of carbon tetrachloride. This was proved by biometric, biochemical and histological findings. 2. Prednisolone increased the toxicity caused by carbon tetrachloride. 3. The group treated with Sosio-Tang extracts. and prednisolon concomitantly increased the toxicity compared with Sosio-Tang extracts. treated group.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.10
• /
• pp.63-68
• /
• 2016

Recently, Biometrics is being magnified than ID or password about user authentication. However, unlike a PIN, password, and personal information there is no way to modify the exposure if it is exposed and used illegally. As FIDO(Fast IDentity Online) than existing server storing method, It stores a user's biometric information to the user device. And the user device authentication using the user's biometric information, the user equipment has been used a method to notify only the authentication result to the server FIDO. However, FIDO has no mutual authentication between the user device and the FIDO server. We use a Certificate Authority in order to mutually authenticate the user and the FIDO server. Thereby, we propose a more reliable method and compared this paper with existed methods about security analysis.

• Journal of Veterinary Clinics
• /
• v.14 no.1
• /
• pp.70-74
• /
• 1997

말과 소의 정상 안구내의 구조와 크기를 알아보기 위하여 10마리의 말과 14두의 Holstein 안구를 적출하여 생리식염수내에서 초음파상으로 안구내의 구조를 확인하였으며 각막의 두께, 전방의 깊이, 수정체의 두께, 초자체의 깊이 및 안구축을 측정하였다. 초음파로 측정한 안구를 $-30{\circ}C$ 로 동결한 후 Diamond cutter로 절단하여 caliper로 측정하여 Student-t test로 처리하여 수치를 비교하였다. 초음파상에서 말은 암컷$(35.99{\pm}1.97)과 숫컷(35.94{\pm} 3.36)$, 좌측(36.26)과 우측$(35.67{\pm}2.65)$눈의 크기가 비슷하였으나, 소에서도 좌측$(29.06{\pm} 3.36)과 우측(28.53{\pm} 3.36)$눈의 크기가 비슷하여 통계학적 유의차는 없었다. 본 연구에서는 7.5MHz 초음파기의 B-Mode 방식을 이용하여 말과 소의 안구의 구조를 확인하고 측정하였는데 임상적으로 매우 유용하여 수의안과학에서 적용할수 있는 가치있는 진단법이다.

• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.131-134
• /
• 2002

As the increased use of computer, wired/wireless/mobile Internet, security in using Internet becomes a more important problem. Thus, biometric technology using physical and behavior characteristics of a person is hot issue. Many different types of biometric technologies of a person such as fingerprint, face, iris, vein, DNA, brain wave, palm, voice, dynamic signature, etc. had already been studied but remained unsuccessful because they do not meet social demands. However, recently many of these technologies have been actively revived and researchers have developed new products on various commercial fields. Dynamic signature verification technology is to verify the signer by calculating his writing manner, speed, angle, and the number of strokes, order, the down/up/movement of pen when the signer input his signature with an electronic pen for his authentication. Then signature verification system collects mentioned above various feature information and compares it with the original one and simultaneously analyzes to decide whether signature is forgery or true. The prospect of signature verification technology is very promising and its use will be wide spread in terms of economy, security, practicality, stability and convenience.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.170-178
• /
• 2017

Biometric recognition is one of the major challenging topics which needs high performance of recognition accuracy. Most of existing methods rely on a single source of biometric to achieve recognition. The recognition accuracy in biometrics is affected by the variability of effects, including illumination and appearance variations. In this paper, we propose a new multimodal biometrics recognition using convolutional neural network. We focus on multimodal biometrics from face and periocular regions. Through experiments, we have demonstrated that facial multimodal biometrics features deep learning framework is helpful for achieving high recognition performance.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.2
• /
• pp.157-163
• /
• 2005

In this paper, we present the multimodal system based on the fusion of two user-friendly biometric modalities: Iris and Face. In order to reach robust identification and verification we are going to combine two different biometric features. we specifically apply 2-D discrete wavelet transform to extract the feature sets of low dimensionality from iris and face. And then to obtain Reduced Joint Feature Vector(RJFV) from these feature sets, Direct Linear Discriminant Analysis (DLDA) is used in our multimodal system. In addition, the Synergetic Neural Network(SNN) is used to obtain matching score of the preprocessed data. This system can operate in two modes: to identify a particular person or to verify a person's claimed identity. Our results for both cases show that the proposed method leads to a reliable person authentication system.