• 제어로봇시스템학회논문지
• /
• 제18권9호
• /
• pp.887-893
• /
• 2012

In this paper, we propose a new approach to extract directional features based on directional patterns of each region in fingerprint images. The proposed approach computes the center of gravity to extract features from fingerprint images of various shapes. According to it, we divide a fingerprint image into four regions and compute the directional values of each region. To extract directional features of each region from a fingerprint image, we spilt direction values of ridges in a region into 18 classes and compute frequency distribution of each region. Through the result of our experiment using FVC2002 DB database acquired by electronic devices, we show that directional features are effectively extracted from various fingerprint images of exceptional inputs which lost all or part of singularities. To verify the performance of the proposed approach, we explained the process to model Arch, Left, Right and Whorl class using the extracted directional features of four regions and analyzed the classification result.

• 전기학회논문지
• /
• 제58권12호
• /
• pp.2529-2531
• /
• 2009

A simple multimodal fingerprint recognition method based on two types of feature vectors such as minutiae points and directional features is proposed, where Directional Filter Bank (DFB) is used to extract directional features. Experimental results show that the proposed method can effectively combine minutiae- and DFB-based methods and produce a better matching capability in the poor quality fingerprint image.

• Journal of information and communication convergence engineering
• /
• 제5권2호
• /
• pp.140-143
• /
• 2007

Fingerprint Recognition System is made up of Off-line treatment and On-line treatment; the one is registering all the information of there trieving features which are retrieved in the digitalized fingerprint getting out of the analog fingerprint through the fingerprint acquisition 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 matching between On-line and Off-line treatment, the most important thing is which features we are going to use as the standard. Therefore, we have been using "Delta" and "Core" as this standard until now, but there might have been some deficits not to exist in every person when we set them up as the standards. In order to handle the users who do not have those features, we are still using the matching method which enables us to make up of the spanning tree or the triangulation with the relations of the spanned feature. However, there are some overheads of the time on these methods and it is not sure whether they make the correct matching or not. In this paper, introduces a new data structure, called Union and Division, representing binary fingerprint image. Minutiae detecting procedure using Union and Division takes, on the average, 32% of the consuming time taken by a minutiae detecting procedure without using Union and Division.

• International Journal of Control, Automation, and Systems
• /
• 제6권6호
• /
• pp.800-808
• /
• 2008

A fingerprint verification system based on a set of invariant moment features and a nonlinear Back Propagation Neural Network(BPNN) verifier is proposed. An image-based method with invariant moment features for fingerprint verification is used to overcome the demerits of traditional minutiae-based methods and other image-based methods. The proposed system contains two stages: an off-line stage for template processing and an on-line stage for testing with input fingerprints. The system preprocesses fingerprints and reliably detects a unique reference point to determine a Region-of-Interest(ROI). A total of four sets of seven invariant moment features are extracted from four partitioned sub-images of an ROI. Matching between the feature vectors of a test fingerprint and those of a template fingerprint in the database is evaluated by a nonlinear BPNN and its performance is compared with other methods in terms of absolute distance as a similarity measure. The experimental results show that the proposed method with BPNN matching has a higher matching accuracy, while the method with absolute distance has a faster matching speed. Comparison results with other famous methods also show that the proposed method outperforms them in verification accuracy.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.901-904
• /
• 2000

A direct authentication from gray-scale image, instead of the conventional multi-step preprocessing, is proposed using Gabor filter-based features from the gray-scale fingerprint around core point. The core point is located as a reference point for the translation invariant matching. And its principal symmetry axis is detected for the rotation invariant matching from its neighboring region centered at the core point. And then fingerprint is divided into non-overlapping blocks with respect to the core point and features are directly extracted form the blocked gray level fingerprint using Gabor filter. The proposed fingerprint authentication is based on the Euclidean distance between the corresponding Gabor features of the input and the template fingerprints. Experiments are conducted on 300${\times}$300 fingerprints obtained from a CMOS sensor with 500 dpi resolution, and the proposed method could lower the False Reject Rate(FRR) to 18.2% under False Acceptance Rate(FAR) of 0%.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.446-449
• /
• 2000

A direct RTI(Rotation and translation invariant) fingerprint identification is proposed using the GCMs(generalized complex moments) and Gabor filter-based features from the grey level fingerprint around core point. The core point is located as reference point for the translation invariant matching. And its symmetry axis is detected for the rotation invariant matching from its neighboring region centered at the core point. And then, fingerprint is divided into non-overlapping blocks with respect to the core point and, in contrast to minutiae-based method using various processing steps, features are directly extracted from the blocked grey level fingerprint using Gabor filter, which provides information contained in a particular orientation in the image. The Proposed fingerprint identification is based on the Euclidean distance of the corresponding Gabor features between the input and the template fingerprint. Experiments are conducted on 300 ${\times}$ 300 fingerprints obtained from the CMOS sensor with 500 dpi resolution, and the proposed method could obtain 97% identification rate.

• Journal of Information Processing Systems
• /
• 제12권1호
• /
• pp.83-99
• /
• 2016

The latest research on the image-based fingerprint matching approaches indicates that they are less complex than the minutiae-based approaches when it comes to dealing with low quality images. Most of the approaches in the literature are not robust to fingerprint rotation and translation. In this paper, we develop a robust fingerprint matching system by extracting the circular region of interest (ROI) of a radius of 50 pixels centered at the core point. Maximizing their orientation correlation aligns two fingerprints that are to be matched. The modified Euclidean distance computed between the extracted orientation features of the sample and query images is used for matching. Extensive experiments were conducted over four benchmark fingerprint datasets of FVC2002 and two other proprietary databases of RFVC 2002 and the AITDB. The experimental results show the superiority of our proposed method over the well-known image-based approaches in the literature.

• 한국콘텐츠학회논문지
• /
• 제17권12호
• /
• pp.281-288
• /
• 2017

금융위원회는 2019년도까지 금융기관 및 공공기관 등에서 보유하고 있는 문서에서 지문 정보를 폐기 조치하라고 통보했다. 이를 위해 문서 영상에서 지문 정보를 검출하고 마스킹하기 위한 상용 솔루션들이 발표되고 있다. 본 논문에서는 문서 영상에 다양한 형태로 기록된 지문 후보들을 분할한 다음 인공신경망 분류기로 지문인지 여부를 판단할 때 지문의 특징이 잘 반영된 피처를 추출하기 위해 다중 LBP 피처를 설계하고 이를 이용해서 지문 정보를 마스킹하는 알고리즘을 제안하였다. 제안한 지문 정보 마스킹 알고리즘을 이용하여 금융권에서 보유하고 있는 3,497장의 문서 영상을 대상으로 지문 마스킹 실험을 수행한 결과 96.4%의 지문을 마스킹 할 수 있어서 본 알고리즘이 실제 지문 정보 마스킹 작업에 효과적으로 활용될 수 있음을 확인하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제35권1호
• /
• pp.41-49
• /
• 2008

지문분류는 지문을 전역특징에 따라 미리 정의된 클래스로 분류하여 대규모 지문식별시스템의 매칭시간을 감소시키는데 유용하다. 그런데, 지문의 고유성으로 인해 전역특징이 다양하게 분포함에도 불구하고, 기존의 지문분류 방법들은 모든 지문에 대해 고정된 영역으로부터 비적응적으로 전역특징을 추출하였다. 본 논문에서는 다양한 지문을 효과적으로 분류하기 위해 각 지문에 적응적으로 특징을 추출하는 방법을 제안한다. 이는 각 지문의 융선 방향의 변화량을 계산하여 적응적으로 특징영역을 탐색한 후, 특징영역내의 융선 방향 값을 특징벡터로 추출하고 지지벡터기계(Support Vector Machines)를 이용해 분류한다. 본 논문에서는 NIST4 데이타베이스를 이용하여 실험을 수행하였다. 그 결과 5클래스 분류에 대해 90.3%, 4클래스 분류에 대해 93.7%의 분류성능을 얻었으며, 비적응적으로 추출한 특징벡터와의 비교실험을 통해 제안하는 적응적 특징추출방법의 유용성을 입증하였다.

• 스마트미디어저널
• /
• 제3권3호
• /
• pp.15-19
• /
• 2014

지문 인식 시스템은 지문인식 장치(fingerprint acquisition device)를 통하여 아날로그(analog) 지문으로부터 변환된 디지털(digital) 지문에서 특이점을 추출하고 추출한 특이점들에 대한 정보를 데이터베이스에 등록하는 오프라인(off-line) 처리와 사용자가 시스템에 접근 할 때 입력한 지문으로부터 특이점을 추출한 후 데이터베이스에 저장되어 있는 특이점들과 정합(matching) 하여 사용자의 시스템 접근 여부를 결정하는 온라인(on-line) 처리로 이루어져 있다. 본 논문에서는 다양한 생체인식시스템 중, 통계 지문 인식 정합 방법인 지문의 특이점 을 사용한다. 좌표를 기준으로서 유사성 거리 측정을 하고, 그리고 특정한 각도, 통계 배포 판에 따라서 지문 인식 모델을 찾는 것이다.