• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.8
• /
• pp.1511-1513
• /
• 2007

A new reference point location method using the cosine component is proposed, where an edge map is defined and used to find the reference point. Because all processes used in the proposed method are performed at the block level, less processing time is required. Experimental results show that the proposed method can effectively detect the reference point with higher speed and accuracy for all types of fingerprints.

• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.114-116
• /
• 2004

Biometrics consist of technologies that support automatic identification or verification of identity based on behavioral or physical traits. Biometrics can authenticate identities since they measure unique individual characteristics including fingerprints, hand geometry, iris, hand vascular patterns and facial characteristics. we review the state of the hand vascular patterns identification technology and compare other competitive authentication technologies such as cryptography, electronic signature and PKI.

• Electronics and Telecommunications Trends
• /
• v.33 no.6
• /
• pp.41-49
• /
• 2018

Mid-infrared optical sensors have a number of compelling advantages for remote sensing and the simultaneous measurement of mixtures. However, they still have difficulties in accurate detection owing to signal interferences among a large number of molecular fingerprints in the mid-infrared band, which result in very slow commercialization. Higher sensitivity and higher selectivity are required to overcome this obstruction in measurement technology. In this paper, we review and analyze the trends of mid-infrared sensor technologies enhancing the sensitivity and selectivity.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.2
• /
• pp.67-73
• /
• 2005

Recently, the social requirement of personal identification techniques has been increasing. Fingerprint recognition is one of the biometries methods that has been widely used for this requirement. This paper proposes the fingerprint matching algorithm that uses the information of the ridge shapes of minutiae. In which, the data of the ridge shape are expressed in one-dimensional discrete-time signals. In our algorithm, we obtain one-dimensional discrete-time signals for ridge at every minutiae from input and registered fingerprints, and find pairs of minutia which have the similar ridge shape by comparing input fingerprint with registered fingerprint, thereafter we find candidates of rotation angle and moving displacement from the pairs of similar minutia, and obtain the final rotation angle and moving displacement value from those candidates set by using clustering method. After that, we align an input fingerprint by using obtained data, and calculate the matching rate by counting the number of corresponded pairs of minutia within the overlapped area of an input and registered fingerprints. As a result of experiment, false rejection rate(FRR) of $18.0\%$ at false acceptance rate(FAR) of $0.79\%$ is achieved.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.93-100
• /
• 2004

This paper presents a method to integrate the multiple impressions of a finger for improving fingerprint verification performance. Small-sized sensor has advantage that it can be used in many application fields. However, sufficiently large impression of fingerprint is not available due to the small sensing area, and this degrades the verification performance of the system. The proposed method overcomes this problem by combining the information of fingerprints for enrollment. To combine the fingerprints, the alignment process is important first of all. In the proposed algorithm multiple impressions of a finger are coarsely aligned using the corresponding minutiae pairs and then are finely aligned using the Distance Map. We construct an integrated template for enrollment in aligned coordinate system Since this integrated template represents the enlarged finger region, the problem that is occurred by using small sensor can be overcome. Experimental results show that the use of the integrated template of multiple impressions improves the performance of the fingerprint verification system.

• The Journal of the Korea Contents Association
• /
• v.20 no.3
• /
• pp.687-694
• /
• 2020

Styrofoam is one of the most commonly used materials in everyday life, such as various packaging containers, toys, and buoys, and is likely to be found in crime scenes. However, due to the structural characteristics of Styrofoam, fingerprints cannot be deposited well. According to previous researches, powdering or cyanoacrylate fuming method was applied for developing fingerprints on Styrofoam. The purpose of this study was to investigate the effect of MMD I through comparative experiments of powdering. As a result of applying powder method and MMD I, MMD I was more effective than powder method on styrofoam.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.209-216
• /
• 2016

Latent fingerprint left on the adhesive sides of tapes can be easily found at a crime scene. Small Particle Reagents(SPR) based on iron oxide($Fe_3O_4$) is a technique for the detection of a latent fingerprint adhesive surface. In this study, found out that the causes affecting the quality of the fingerprints developed when used SPR based on iron oxide. To a suspension of 0.5g of iron oxide in 100ml of distilled water, 0.5ml or more surfactant were added can be developed latent fingerprints of good quality. In addition, using surfactants HLB(hydrophile-lipophile balance) value of 11~18 showed good contrast to the background and latent fingerprint.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.1
• /
• pp.39-47
• /
• 2017

Nowadays, there have been an increasing number of illegal use cases where people try to fabricate the working hours by using fake fingerprints. So, the fingerprint liveness detection techniques have been actively studied and widely demanded in various applications. This paper proposes a new method to detect fake fingerprints using CNN (Convolutional Neural Ntworks) based on the patches of fingerprint images. Fingerprint image is divided into small square sized patches and each patch is classified as live, fake, or background by the CNN. Finally, the fingerprint image is classified into either live or fake based on the voting result between the numbers of fake and live patches. The proposed method does not need preprocessing steps such as segmentation because it includes the background class in the patch classification. This method shows promising results of 3.06% average classification errors on LivDet2011, LivDet2013 and LivDet2015 dataset.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.631-646
• /
• 2020

The government is pursuing a policy to remove plug-ins for public and private websites to create a convenient Internet environment for users. In general, financial institution websites that provide financial services, such as banks and credit card companies, operate fraud detection system(FDS) to enhance the stability of electronic financial transactions. At this time, the installation software is used to collect and analyze the user's information. Therefore, there is a need for an alternative technology and policy that can collect user's information without installing software according to the no-plug-in policy. This paper introduces the device fingerprinting that can be used in the standard web environment and suggests a guideline to select from various techniques. We also propose a user authentication model using device fingerprints based on machine learning. In addition, we actually collected device fingerprints from Chrome and Explorer users to create a machine learning algorithm based Multi-class authentication model. As a result, the Chrome-based Authentication model showed about 85%~89% perfotmance, the Explorer-based Authentication model showed about 93%~97% performance.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.397-402
• /
• 2003

This paper proposes an efficient fixed-point (FP) algorithm for improving performances of the independent component analysis (ICA) based on neural networks. The proposed algorithm is the FP algorithm based on Newton method for ICA using the adaptive learning parameters. The purpose of this algorithm is to improve the separation speed and performance by using the learning parameters in Newton method, which is based on the first order differential computation of entropy optimization function. The learning rate and the moment are adaptively adjusted according to an updating state of inverse mixing matrix. The proposed algorithm has been applied to the fingerprints and the images generated by random mixing matrix in the 8 fingerprints of 256${\times}$256-pixel and the 10 images of 512$\times$512-pixel, respectively. The simulation results show that the proposed algorithm has the separation speed and performance better than those using the conventional FP algorithm based on Newton method. Especially, the proposed algorithm gives relatively larger improvement degree as the problem size increases.