Earticle

최근 GPS와 Wi-Fi가 내장된 스마트폰의 보급으로 이를 이용한 위치기반 서비스 (Location-based Service)가 발전하고 있다. 하지만 위치기반 서비스들의 오차 범위는 3∼4m 내외로 크기 때문에 사용자들은 더 정확한 위치를 제공하기를 바라고 있다. 본 논문에서 위치기반 서비스의 핵심기능을 담당하는 측위기술 중 흔히 사용되고 있는 삼각측량법을 활용하여 핑거프린트 방법의 측위오차를 줄일 수 있는 방안을 연구하였 고 프로그램으로 구현한 후 테스트를 실시하였다. 프로그램은 Labview2010으로 구현 하였고, 각각의 알고리즘을 모듈화하여 필터링 적용 전 후 및 개선효과를 비교하기 쉽 도록 구성하였다. 실내 테스트는 인하대학교의 강의실에서 실시하였고 실외 테스트는 인하대학교 운동장에서 실시하였다. 테스트 결과 실내의 경우 본 논문에서 제시하는 필터링 방법을 적용하기 전의 오차가 1.02미터에서 0.83미터로 감소하였고 실외에서는 0.74미터에서 0.54미터로 오차가 감소하였다.

근래의 위치 측위 방법으로 GPS(Global Positioning System) 위성정보를 활용하는 전파항법 방 식을 많이 사용하고 있다. GPS 활용범위가 넓어지고 다양한 측위 정보를 기반으로 하는 분야가 생기면서 보다 높은 정확도를 얻기 위한 새로운 방법들이 요구되고 있다. 자율주행차의 경우 IMU(Inertial Measurement Unit)를 사용한 항법 시스템인 INS(Inertial Navigation System)와 차량 내 부 센서를 이용한 DR(Dead Reckoning) 알고리즘을 사용하여 GPS의 정확도 저하나 음영지역에서 의 위치 측정방법으로 사용하고 있다. 그러나 이러한 측위 방법은 대형화되는 빌딩 지역, 터널, 지하 주차장 등 다양한 음영지역과 시간이 지남에 따라 오차가 계속 증가하는 누적 기반 위치추 정 방법의 한계로 인해 많은 문제 요소가 있다. 본 논문은 GPS 음영지역에서 차량의 위치 측위를 위해, 대중적 무선 통신인 WLAN을 이용한 Fingerprint 기법을 4개의 Anchor 형태로 AP(Access Point)와 지향성 안테나를 위치하여 넓은 지하 주차공간에서 효율적인 측위 방법을 제시하고 시간 이 지남에 따라 주차된 차량이 이동하는 환경에서도 변화가 없는 위치 측위 결과를 입증하였다.

Recently, the radio navigation method utilizing the GPS(Global Positioning System) satellite information is widely used as the method to measure the position of objects. As GPS applications become wider and fields based on various positioning information emerge, new methods for achieving higher accuracy are required. In the case of autonomous vehicles, the INS(Inertial Navigation System) using the IMU(Inertial Measurement Unit), and the DR(Dead Reckoning) algorithm using the in-vehicle sensor, are used for the purpose of preventing degradation of accuracy of the GPS and to measure the position in the shadow area. However, these positioning methods have many elements of problems due not only to the existence of various shaded areas such as building areas that are continually enlarged, tunnels, underground parking lots and but also to the limitations of accumulation-based location estimation methods that increase in error over time. In this paper, an efficient positioning method in a large underground parking space using Fingerprint method is proposed by placing the AP(Access Points) and directional antennas in the form of four anchors using WLAN, a popular means of wireless communication, for positioning the vehicle in the GPS shadow area. The proposed method is proved to be able to produce unchanged positioning results even in an environment where parked vehicles are moved as time passes.

Location-Based Service(LBS) is a service that provides a variety of convenience in life using location information that can be obtained by mobile communication network or satellite signal. In order to provide LBS precisely and efficiently, we need the location determination technology, platform technology and server technology. In this study, we studied on how we can reduce the error on location determination of objects such people and things. Fingerprint location determination method was applied to this study because it can be used at current wireless communication infrastructure and less influenced by a variety of noisy environment than other location determination methods. We converted the probability value to logarithmic scale value because using the sum of k probability values is not suitable to be applied to weight determination. In order to confirm the performance of suggested method, we developed location determination test program with Visual Basic 6.0 and performed the test. According to indoor and outdoor test results, the suggested stochastic method reduced the distance error by 17%, 18% and 9% respectively at indoor environment and 25%, 11% and 4% at outdoor environment compared with deterministic NN, kNN and kWNN fingerprint methods.

지문은 식별 및 검증의 단순성, 변별성, 지문 변화가 없는 특징을 가지고 있다. 또한, 전용 센서를 이용한 지문 획득 및 인식의 속도가 빨라 IoT 장비 또는 단말기 인증수단으로 폭넓게 활용되고 있다. 최근 개인 소형 장 치가 많아지면서 지문 센서의 크기가 작아졌기 때문에 한 번의 스캔으로 획득할 수 있는 이미지 범위도 좁아지고 있어 지문의 일부 이미지를 이용한 개인 식별에 문제점을 가지고 있다. 본 논문에서는 딥러닝을 이용하여 지문의 부분 이미지를 기반으로 사용자를 식별하는 방법을 제안한다. 특징점이 포함된 지문 이미지를 기반으로 부분 지문 이미지로 생성하고, 효과적인 학습을 위해 획득한 이미지에 대한 데이터 증식을 수행한다. 제안 방법을 이용하여 학습 및 테스트한 결과 부분 지문 이미지 60개에 대해 95%, 데이터 증강을 이용한 300개의 부분 지문 이미지에 대해서는 97%의 정확도를 획득했다. 제안 방법은 스마트밴드 등의 개인 소형 스마트기기에서 지문을 이용한 개인 식별 방법에 활용될 수 있다.

The fingerprint has the characteristics of simple identification and verification, distinctiveness, and no fingerprint change. Also, the speed of fingerprint acquisition and recognition using a dedicated sensor is fast, so it is widely used as an authentication method for IoT devices. Recently, the size of the fingerprint sensor of a device has become smaller. Accordingly, the range of fingerprints that can be acquired by one scan is also narrowed. This has a problem in personal identification using a partial fingerprint image. In this paper, we proposed a method to identify users based on partial fingerprint images using deep learning. A partial fingerprint image is generated based on the fingerprint image including feature points. For effective learning, data augmentation is performed on acquired images. In addition, data augmentation of the partial fingerprint image. As a result of learning and testing using the method proposed in this paper, 95% accuracy was obtained for 60 partial fingerprint images. In addition, 97% accuracy was obtained for 300 partial fingerprint images using data augmentation. The proposed method can be used for personal identification using fingerprints in personal small smart devices such as smart bands.

This thesis is on fingerprint recognition method and system, more in detail, the layered fingerprint recognition method and system to compare not only the minutiae or singular point, but also compare the images of detailed area for making prompt and accurate comparison of fingerprint. Through the experiment that applies this theory, we have confirmed that there is a great improvement of verification rate and erroneous recognition rate of other person’s fingerprint. In the world security market, the size of the biometric industry is gradually increasing, of which the fingerprint verification is recognized of its superiority and marketability in terms of relatively low cost, light weight and uneasiness to input bio-information, compared to other biometric methods. This paper proposes a method to utilize the strengths of the Multi-Stage Fingerprint Recognition Method for Fingerprint Payment Verification System. The example of the utilization of the credit card payment is the model business of fingerprint verification credit card payment applied for three months in large domestic marts, to discuss the possibility to settle the non-medium credit trading by the biometric technology and the applicability to the financial services.

Fingerprint recognition systems are the top topics of biometric research and more researchers’ effort is provided to improve high accuracy and speed. Matching methods based on the minutiae points are commonly used and are effective in practice. Algorithms which based on minutia triplets among them are attractive matchers. However, recognizing fingerprints in poor quality images, direction changed, size different fingerprints and so forth is still a very complex job. To overcome these drawbacks, a fingerprint match method used minutiae-based triangular acreage is described here to improve matching accuracy.

In the terms of indoor positioning, the location of the fingerprint technology that based on receiving wireless LAN WIFI signal strength (RSS) has been widely used. In the process of location of fingerprint offline training, the traditional method has more manpower and time. In this paper, we propose a location of fingerprint database constructing method that based on Gaussian process regression (GPR), compared with the process of the traditional method for collecting a large number of fingerprint, now we based on the propagation law of space radio signals, the Gaussian process regression model is applied to the construction of the location fingerprint database, and forecast the location of fingerprint inside the located area through the study of collected samples, by doing this we can reduce the collecting density of fingerprint samples, improve the efficiency of position fingerprint positioning technology.

The Accurate indoor localization is a challenging task due to the absence of GPS. Among numerous proposals, Wifi fingerprint-based localization is one of the most promising approach, since most buildings are nowadays equipped with Wifi access points for wireless network coverage. Due to the nature of Wifi access points in which any user can deploy and manage their own, fingerprints from some access points lead to estimation errors. Location estimation algorithms should consider these factors and be able to locate users with low error distance. Finding the nearest neighbor using Euclidean distance in signal space is most widely used method in estimating location. However, this paper shows that Euclidean distance is prone to error when unstable access points are present. Also, Euclidean distance does not differentiate strong signals and weak signals, which can also mislead location estimation. We propose a different way to determine the nearest neighbor, which penalizes signals from unstable access points, and signifies strong signals compared to weak signals. Experiments with real measurements show that the proposed algorithm reduces mean error distance by 57% and 90-percentile error distance by 64% compared to the Euclidean distance method.

Most of the existing fingerprint retrieval systems are based on the overall characteristics and detailed features of fingerprints, and their performance is poor in the cases of low-quality fingerprint images, such as incomplete fingerprint images. In order to improve the recognition speed, accuracy, and robustness of automated fingerprint recognition systems based on large-scale fingerprint databases, in this paper, we propose a fast fingerprint classification retrieval and identification method based on Scale Invariant Feature Transform (SIFT) and Local Sensitive Hash (LSH) algorithms. A method based on scale space theory extracts SIFT feature point descriptors of relatively high-quality fingerprint images in accordance with the principle of a greater matching contribution rate, uses multi-template image feature fusion technology to build a stable fingerprint feature template database, achieves the storage and retrieval of high-dimensional SIFT features using the LSH algorithm, and carries out matching progressively by level on the basis of SIFT’s matching principle of close neighboring priority scale. Experimental results show that the proposed method has strong penetration, high retrieval efficiency, good recognition accuracy, and strong robustness, thereby providing a fast and efficient retrieval and matching mechanism for the automated recognition of the large-scale fingerprint database, with strong practicality.

The use of fingerprint for human identity management has been on the rise lately. Reasons adduced for this include its high level of uniqueness, availability, consistency and universality. The task of human identity management based on fingerprint technology involves a number of processes which include enrolment, enhancement, feature and singular points detection and extraction and pattern matching. Detection and extraction of genuine and reliable feature and singular points are paramount for reliable pattern matching. The limitations of some existing fingerprint singular point detection algorithms include inaccurate detection and failure with some fingerprint pattern and poor quality images. In this paper, a modified Poincare Index fingerprint singular point detection algorithm is proposed for resolving these limitations. The results of the experimental study of the new algorithm on Dataset DB1 of FVC2000 standard fingerprint database show that the new algorithm reliably and adequately detected singular points from fingerprints of all patterns and qualities.

일선현장에서 발견되는 변사체 중, 탄화, 건조, 수중시체에 대하여는 지문채취가 쉽지 않은 것이 현실이다. 이렇게 지문현출이 불가능하다고 생각하였던 탄화, 건조, 수중시체에 대하여 지문현출을 시도하였다. 탄화시체는, 근육의 굳음과 수축으로 인해 투사형 자세를 취하고, 손은 주먹을 쥐고 있는 형상으로 발견되는 경우가 대부분으로, 이때 주먹을 쥐고 있는 중지 손가락의 안쪽에서 손상이 적음을 본 연구를 통해 알게 되어 이를 정제수에 불려 표피를 분리한 다음, 건조 후, Scotch Pad로 전사하는 방법이 효과적인 현출방법임을 확인할 수 있었다. 건조시체는, 지두(the tip of a finger)의 표피가 딱딱하게 굳으면서 굴곡되어 그곳에 수분을 공급함으로써 지두 표피가 원상회복되는 것을 지문잉크로 현출하는 방법이 효과적인 현출방법임을 확인할 수 있었다. 수중시체는, 수중에서 인체의 지방이 가수분해되어 지방산염등이 형성, 시랍화가 된다. 이를 알콜솜으로 여러번 닦아내어 수분을 탈수하는 방법, 헤어드라이의 뜨거운 바람을 쐬여 수분과 지방을 탈수하는 방법, 손상된 표피를 제거하고 진피지문을 고온처리법을 활용하여 현출하는 방법 등이 가장 효과적인 현출 방법임을 확인하고 앞으로도 계속된 연구를 통하여 더욱 효율적인 지문 현출 방법을 찾아야 할 것이다.

Until today, it is still difficult to take fingerprints off from the charred, dried and wet (the body that was in the water) bodies. Although it's impossible, I tried doing fingerprint detection on those three types of bodies. In charred body, it is almost a pugilistic attitude because of a muscle contraction and hardened and made a fist. As founding the middle finger of the fist gets a little injured, the epidermis separates out from soaking the middle finger in distilled water. Then, after dry, it transfers to Scotch Pad. In mummy, as the epidermis of fingertip becomes hard and made a curve can take a water, it gets back and prints using fingerprint’s ink. In wet body, it becomes adipocerous because fatty acids are produced by the hydrolysis. Body can be dehydrated because of rubbing with alcohol cotton and hot winds of hair dryer. And after remove the injured epidermis, high temperature processing the fingerprint of dermis. I can prove those ways are best ways today, and as continuous study, we’ll be finding better to take fingerprints in the future.

지문 인식 시스템은 지문인식 장치를 통하여 아날로그 지문으로부터 변환된 디지털 지문에서 특이 점을 추출하고 추출한 특이점들에 대한 정보를 데이터베이스에 등록하는 오프라인 처리와 사용자가 시스템에 접근 할 때 입력한 지문으로부터 특이점을 추출한 후 데이터베이스에 저장되어 있는 특이 점들과 정합 하여 사용자의 시스템 접근 여부를 결정하는 온라인 처리로 이루어져 있다. 본 논문에서 는 다양한 생체인식시스템 중, 통계 지문 인식 정합 방법인 지문의 특이점을 사용한다. 좌표를 기준 으로서 유사성 거리 측정을 하고, 그리고 특정한 각도, 통계 배포 판에 따라서 지문 인식 모델을 찾 는 것이다.

FINGERPRINT Recognition System is made up of Off-line treatment and On-line treatment; the one is registering all the information of there trier features which are retrieved in the digitalized fingerprint getting out of the analog fingerprint through the fingerprint recognition device and the other is the treatment making the decision whether the users are approved to be accessed to the system or not with matching them with the fingerprint features which are retrieved and database from the input fingerprint when the users are approaching the system to use. In this paper, Among various biometrics recognition systems, statistical fingerprint recognition matching methods are considered using minutiae on fingerprints. We define similarity distance measures based on the coordinate and angle of the minutiae, and suggest a fingerprint recognition model following statistical distributions.

의심문서에 유류된 잠재지문을 안정적으로 현출할 수 있는 새로운 불소계(CFs) 화합물을 탐색 하고자, 습윤지수(WI)에 관한 정량적인 구조와 물리-화학적인 성질과의 관계를 설명하는 최적화 된 QSPR 모델 No.5 (R2= 0.90)를 유도하고 FC-72 용매를 예측하였다. 그리고 유류된 잠재지문 중 아미노산에 대하여 Ninhydrin 방법보다 민감한 Dansyl 방법으로 acetone, HFE-7100 및 예측된 FC-72 등 3가 지 용매중에서 잠재지문 현출실험을 실행하였다. 또한, 용매분자의 소수성(logP)과 습윤지수(WI) 사이 에 성립하는 유의미한 비례관계로부터 실습윤지수의 86% (100*R2)를 설명할 수 있는 유용한 모델 No. 4를 얻었다. 그러므로 용매들의 소수성(logP)에 관한 모델 No. 4에 근거하여 최적화 된 QSPR 모델 No. 5는 불소계(CFs) 지문현출 용매를 탐색하는 목적으로 효과적인 수단이 될 수 있을 것이다. Dansyl 방법에 의한 지문현출 결과로부터 예측된 FC-72 용매는 HFE-7100 용매에 비하여 양호하였으며 특히, 액상 현출제임에도 불구하고 비다공성 재질에서 양호한 현출성을 나타내었다.

To search new fluorine family (CFs) compounds as carrier solvent that can stably detecting from the latent fingerprint deposited on the suspicious document in the forensic science, the optimized QSPR (Quantitative structure -property relationship) model No. 5 (R=0.90) on Wetting index (WI) was derived and predicted the FC-72 solvent. And latent fingerprint detection experiments were carried out in three carrier solvents, acetone, HFE-7100 and predicted FC-72 by Dansyl method. This method is more sensitive than Nihydrin method to amino acids in deposited latent fingerprints. Also, useful the model No.4 that can explain 86% (100*R2) of real wetting index from the meaningful proportional relationships between hydrophobicity (logP) of solvents and wetting index (WI) was obtained. Therefore, based on the Model No.5 for hyrophobicity of solvents, the optimized QSPR model No.5 would be able to an effective way in searching of fluorine family (CFs) fingerprint detection solvents. From the results of fingerprint detection by Dansyl method, it was found that the predicted solvent FC-72 was more effective as compared to HFE-7100 solvent. Particularly, it shows very good detection rate on the nonporous materials even though FC-72 solvent is liquid phase detection agent.

실내에서의 위치를 추정하기 위한 기술 연구가 활발하게 진행되고 있다. 특히 추가적인 기반 시설을 필요로 하지 않는 WiFi fingerprint 방식은 경제성이 높아서 부분적으로 실용화되고 있다. 사전에 여러 지점에서 측정된 무선 랜 수신 신호의 세기 정보와 추후에 특정 지점에서 측정된 세기 정보를 비교하여 유사한 지점을 해당 지점으로 추정하 는 KNN 방식은 간단하지만 성능이 좋다. 그러나 기존의 KNN 방식은 평균하는 후보 위치들의 개수 K가 일정하므로, 특정 지점에 따라 위치 추정 오차가 최적화되지 못하는 문제가 있다. 본 논문에서는 특정 지점마다 K 값을 적응적으로 변화시키는 KNN 방식에서 평균 범위를 설정하는 알고리즘을 제안하고 실험 데이터에 적용하여 그 성능을 평가하였다.

Research on the technique for estimating the indoor position has been actively carried out. In particular, the WiFi fingerprint method, which does not require any additional infrastructure, is being partially used because of its high economic efficiency. The KNN method which estimates similar points to the corresponding points by comparing intensity information of the WLAN reception signal measured at various points in advance with intensity information measured at a specific point in the future is simple but has a good performance. However, in the conventional KNN scheme, since the number K of average candidate positions is constant, there is a problem that the position estimation error is not optimized according to a specific point. In this paper, we proposed an algorithm that adaptively changes the K value for each point and applied it to experimental data and evaluated its performance.

The present of state is situation that is realized by necessity of maintenance of public security about great many information is real condition been increasing continually in knowledge info-age been situating in wide field of national defense, public peace, banking, politics, education etc. Also, loss or forgetfulness, and peculation by ID for individual information and number increase of password in Internet called that is sea of information is resulting various social problem. By alternative about these problem, including Biometrics, several authentication systems through sign(Signature), Smart Card, Watermarking technology are developed. Therefore, This paper shows that extract factor that efficiency can get into peculiar feature in physical features for good fingerprint recognition algorithm implementation with old study finding that take advantage of special quality of these fingerprint.

Among various biometrics recognition systems, statistical fingerprint recognition matching methods are considered using minutiae on fingerprints. We define similarity distance measures based on the coordinate and angle of the minutiae, and suggest a fingerprint recognition model following statistical distributions. We could obtain confidence intervals of similarity distance for the same and different persons, and optimal thresholds to minimize two kinds of error rates for distance distributions. It is found that the two confidence intervals of the same and different persons are not overlapped and that the optimal threshold locates between two confidence intervals. Hence an alternative statistical matching method can be suggested by using nonoverlapped confidence intervals and optimal thresholds obtained from the distributions of similarity distances.

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.