On analysis of rural and urban indian fingerprint images
04 Jan 2010-pp 55-61
TL;DR: The analysis shows that rural population is very challenging and existing algorithms/systems are unable to provide acceptable performance and fingerprint recognition algorithms provide comparatively better performance on urban population.
Abstract: This paper presents a feasibility study to compare the performance of fingerprint recognition on rural and urban Indian population. The analysis shows that rural population is very challenging and existing algorithms/systems are unable to provide acceptable performance. On the other hand, fingerprint recognition algorithms provide comparatively better performance on urban population. The study also shows that poor images quality, worn and damaged patterns and some special characteristics affect the performance of fingerprint recognition.
Citations
More filters
01 Sep 2014
TL;DR: This paper has used the rural fingerprints database which is collected from IIIT Delhi research lab which consists of 1632 fingerprints images and pre-preprocessed 1632 sample images using De-noising techniques use for image enhancement and tried to improve the quality of images.
Abstract: Identification and authentication is done using various biometric sign like fingerprints. The recognition rate of correct person is depending on quality of fingerprints images. Fingerprints quality also varying from rural and urban population. Rural population having more physical work than urban population. Therefore the ridges, valleys, bifurcation, joints, minutia etc. features are not good quality hence it reduces recognition rate accuracy. To improve recognition rate of such images there is strong need to first improve the quality of features. In this paper we have used the rural fingerprints database which is collected from IIIT Delhi research lab which consists of 1632 fingerprints images. Out of which we have pre-preprocessed 1632 sample images using De-noising techniques use for image enhancement and tried to improve the quality of images. The resultant images quality is verified by using different enhancement, it is found that quality has been improved. Hence it is proved that the recognition rate is increases.
1 citations
Dissertation•
01 Dec 2014
TL;DR: In this thesis, two novel schemes have been proposed: one scheme on dots and incipient ridges extraction and another scheme on matching using level 2 and level 3 features.
Abstract: In this thesis, two novel schemes have been proposed: one scheme on dots and incipient ridges extraction and another scheme on matching using level 2 and level 3 features. Dots and incipient ridges are extracted by tracing valley. Starting points are found on the valley by analyzing the frequencies present in the fingerprint. Valleys are traced from the starting point using Fast Marching Method (FMM). An intensity based checking method is used for finding these feature points. Delaunay triangle has been constructed using level 2 feature. A novel algorithm of selecting compatible triangle pair from Delaunay triangle is proposed. A novel set of feature parameters are constructed by establishing spatial relation between minutiae and dots-and-incipient.
Pore based matching has been performed using Robust Affine Iterative Closest Point algorithm. These extended features (dots, incipient ridges, and pores) are helpful for forensic experts. However, forensic experts deal with full-to-partial print matching of latent fingerprint. Hence, Full-to-partial fingerprint matching has been carried out. Partial print is constructed by cropping a window from a full fingerprint in two ways such as, non-overlapped cropping and random cropping. Form the experiment, it has been observed that random cropping based fingerprint has better accuracy than non-overlapped cropping. For performance evaluation of the proposed algorithm, two public databases have been used: NIST SD30 database and IIIT Delhi rural database. All images in SD30 are taken in constrained environment and images in IIIT database are taken in unconstrained environment. Feature level and score level fusion have been carried out for fusing different levels of feature. It has been observed that score level fusion shows better accuracy than feature level fusion.
1 citations
Cites methods from "On analysis of rural and urban indi..."
...For performance evaluation of the proposed algorithm, two public databases have been used: NIST SD30 database and IIIT Delhi rural database....
[...]
...4 4.1 Accuracy comparison of proposed extracted feature with BOZORTH3 matching with Yi Chen’s approach for level 2 and level 2 with level 3 features using SD 30 and IIIT Delhi database. . . . . . . . . . . . . . 55 4.2 Accuracy comparison of proposed extracted feature and proposed matching with Yi Chen’s approach for level 2 and level 2 with level 3 features using SD 30 and IIIT Delhi database. . . . . . . . . . . . . 56 4.3 Accuracy table of sum rule based fusion of RAICP and Delaunay triangle based matching score on SD 30 and IIIT Delhi database. . . 59 ix Chapter 1...
[...]
...(b) 3D mesh representation of pores . . . 40 4.1 Block diagram of score level fusion . . . . . . . . . . . . . . . . . . . 44 4.2 (a) Delaunay triangle constructed using minutiae, (b) Features extracted from triangle . . . . . . . . . . . . . . . . . . . . . . . . . 50 4.3 ROC using SD 30 database (a) non-overlapped cropping using only level 2 features, (b) non-overlapped cropping using level 2 and level 3 features, (c) random cropping using only level 2 features, (d) random cropping using level 2 and level 3 features . . . . . . . . . . . . . . . 57 4.4 ROC using IIIT Delhi database (a) random cropping using level 2 and level 3 features, (b) non-overlapped cropping using only level 2 features, (c) non-overlapped cropping using level 2 and level 3 features, (d) random cropping using only level 2 features . . . . . . . . . . ....
[...]
...We have used NIST special database 30 (SD30) [4] and Rural Indian Fingerprint Database [5] of IIIT Delhi for performance evaluation....
[...]
...Experimental results are obtained using various available datasets such as National Institute of Standards and Technology (NIST) special database 30 (SD30) [4] and Rural Indian Fingerprint Database of IIIT Delhi [5]....
[...]
01 Dec 2014
TL;DR: Extraction technique of two extended features, dots and incipient ridges by tracing valleys is presented to show the superiority of the proposed feature extraction technique over state of art.
Abstract: Automated Fingerprint Identification Systems (AFIS) currently rely only on Level 1 and Level 2 features. But these features are not much helpful for forensic experts as the experiment deals with partial to full print matching of latent fingerprint. Forensic experts takes the advantage of extended feature proposed by “Committee to Define an Extended Fingerprint Feature Set” (CDEFFS). This paper presents extraction technique of two extended features, dots and incipient ridges by tracing valleys. We have found starting points on the valley by analyzing the frequencies present in the fingerprint. Valley are traced from the starting point using first marching method ( FMM ). Then an intensity checking method is used for finding these features. Extensive simulation is carried out in MATLAB environment to show the superiority of the proposed feature extraction technique over state of art. Accuracy of the proposed feature extraction scheme also has been shown using special database 30 and IIIT Delhi database.
1 citations
Cites methods from "On analysis of rural and urban indi..."
...We have used NIST special database 30 (SD30) [12] and Rural Indian Fingerprint Database [7] of IIIT Delhi for performance evaluation....
[...]
...Similarly, in case of Rural Indian Fingerprint Database, the first image is divided into 12 non-overlapping block of size 150×150 and rest pixels are discarded at boundary....
[...]
DOI•
TL;DR: CA-GAN is explicitly regularized to learn spatial context by ensuring that the model not only performs fingerprint restoration but also accurately predicts the correct spatial arrangement of randomly arranged fingerprint patches.
Abstract: The literature on fingerprint restoration algorithms firmly advocates exploiting contextual information, such as ridge orientation field, ridge spacing, and ridge frequency, to recover ridge details in fingerprint regions with poor quality ridge structure. However, most state-of-the-art convolutional neural network based fingerprint restoration models exploit spatial context only through convolution operations. Motivated by this observation, this article introduces a novel context-aware fingerprint restoration model: context-aware GAN (CA-GAN). CA-GAN is explicitly regularized to learn spatial context by ensuring that the model not only performs fingerprint restoration but also accurately predicts the correct spatial arrangement of randomly arranged fingerprint patches. Experimental results establish better fingerprint restoration ability of CA-GAN compared to the state-of-the-art.
TL;DR: This paper proposes a new scheme that can model the pair-relationship of two latent fingerprints directly as the similarity feature for recognition, and shows that the proposed method outperforms the state of the art.
Abstract: —Latent fingerprints are important for identifying criminal suspects. However, recognizing a latent fingerprint in a collection of reference fingerprints remains a challenge. Most, if not all, of existing methods would extract representation features of each fingerprint independently and then compare the similarity of these representation features for recognition in a different process. Without the supervision of similarity for the feature extraction process, the extracted representation features are hard to optimally reflect the similarity of the two compared fingerprints which is the base for matching decision making. In this paper, we propose a new scheme that can model the pair-relationship of two fingerprints directly as the similarity feature for recognition. The pair-relationship is modeled by a hybrid deep network which can handle the difficulties of random sizes and corrupted areas of latent fingerprints. Experimental results on two databases show that the proposed method outperforms the state of the art.
References
More filters
Book•
10 Mar 2005TL;DR: This unique reference work is an absolutely essential resource for all biometric security professionals, researchers, and systems administrators.
Abstract: A major new professional reference work on fingerprint security systems and technology from leading international researchers in the field Handbook provides authoritative and comprehensive coverage of all major topics, concepts, and methods for fingerprint security systems This unique reference work is an absolutely essential resource for all biometric security professionals, researchers, and systems administrators
3,821 citations
"On analysis of rural and urban indi..." refers background in this paper
...Fingerprints are considered reliable to identify individuals and are used in both biometric and forensic applications [1]....
[...]
TL;DR: An improved version of the minutia extraction algorithm proposed by Ratha et al. (1995), which is much faster and more reliable, is implemented for extracting features from an input fingerprint image captured with an online inkless scanner and an alignment-based elastic matching algorithm has been developed.
Abstract: Fingerprint verification is one of the most reliable personal identification methods. However, manual fingerprint verification is incapable of meeting today's increasing performance requirements. An automatic fingerprint identification system (AFIS) is needed. This paper describes the design and implementation of an online fingerprint verification system which operates in two stages: minutia extraction and minutia matching. An improved version of the minutia extraction algorithm proposed by Ratha et al. (1995), which is much faster and more reliable, is implemented for extracting features from an input fingerprint image captured with an online inkless scanner. For minutia matching, an alignment-based elastic matching algorithm has been developed. This algorithm is capable of finding the correspondences between minutiae in the input image and the stored template without resorting to exhaustive search and has the ability of adaptively compensating for the nonlinear deformations and inexact pose transformations between fingerprints. The system has been tested on two sets of fingerprint images captured with inkless scanners. The verification accuracy is found to be acceptable. Typically, a complete fingerprint verification procedure takes, on an average, about eight seconds on a SPARC 20 workstation. These experimental results show that our system meets the response time requirements of online verification with high accuracy.
1,376 citations
TL;DR: A filter-based fingerprint matching algorithm which uses a bank of Gabor filters to capture both local and global details in a fingerprint as a compact fixed length FingerCode and is able to achieve a verification accuracy which is only marginally inferior to the best results of minutiae-based algorithms published in the open literature.
Abstract: Biometrics-based verification, especially fingerprint-based identification, is receiving a lot of attention. There are two major shortcomings of the traditional approaches to fingerprint representation. For a considerable fraction of population, the representations based on explicit detection of complete ridge structures in the fingerprint are difficult to extract automatically. The widely used minutiae-based representation does not utilize a significant component of the rich discriminatory information available in the fingerprints. Local ridge structures cannot be completely characterized by minutiae. Further, minutiae-based matching has difficulty in quickly matching two fingerprint images containing a different number of unregistered minutiae points. The proposed filter-based algorithm uses a bank of Gabor filters to capture both local and global details in a fingerprint as a compact fixed length FingerCode. The fingerprint matching is based on the Euclidean distance between the two corresponding FingerCodes and hence is extremely fast. We are able to achieve a verification accuracy which is only marginally inferior to the best results of minutiae-based algorithms published in the open literature. Our system performs better than a state-of-the-art minutiae-based system when the performance requirement of the application system does not demand a very low false acceptance rate. Finally, we show that the matching performance can be improved by combining the decisions of the matchers based on complementary (minutiae-based and filter-based) fingerprint information.
1,207 citations
"On analysis of rural and urban indi..." refers methods in this paper
...– Implementation of minutiae feature extraction and matching [2] termed as Algorithm - A – Implementation of filterbank based feature extraction and matching [3] termed as Algorithm - B – Two commercial fingerprint recognition systems, termed as System - C and System - D(1)...
[...]
TL;DR: In this article, a filter bank based fingerprint representation is implemented and the overall performance of the developed system is tested and the results have shown that this system can be used effectively for secure online verification applications.
Abstract: As organizations search for more secure authentication methods for user access, e-commerce, and other security applications, biometrics is gaining increasing attention. With an increasing emphasis on the emerging automatic personal identification applications, fingerprint based identification is becoming more popular. The most widely used fingerprint representation is the minutiae based representation. The main drawback with this representation is that it does not utilize a significant component of the rich discriminatory information available in the fingerprints. Local ridge structures cannot be completely characterized by minutiae. Also, it is difficult quickly to match two fingerprint images containing different number of unregistered minutiae points. In this study filter bank based representation, which eliminates these weakness, is implemented and the overall performance of the developed system is tested. The results have shown that this system can be used effectively for secure online verification applications.
69 citations
TL;DR: A novel online fingerprint verification algorithm and distribution system that is insensitive to fingerprint image distortion, scale, and rotation, and robust even on poor quality fingerprint images is proposed.
Abstract: In this paper, a novel online fingerprint verification algorithm and distribution system is proposed. In the beginning, fingerprint acquisition, image preprocessing, and feature extraction are conducted on workstations. Then, the extracted feature is transmitted over the internet. Finally, fingerprint verification is processed on a server through web-based database query. For the fingerprint feature extraction, a template is imposed on the fingerprint image to calculate the type and direction of minutiae. A data structure of the feature set is designed in order to accurately match minutiae features between the testing fingerprint and the references in the database. An elastic structural feature matching algorithm is employed for feature verification. The proposed fingerprint matching algorithm is insensitive to fingerprint image distortion, scale, and rotation. Experimental results demonstrated that the matching algorithm is robust even on poor quality fingerprint images. Clients can remotely use ADO.NET on their workstations to verify the testing fingerprint and manipulate fingerprint feature database on the server through the internet. The proposed system performed well on benchmark fingerprint dataset.
7 citations
"On analysis of rural and urban indi..." refers methods in this paper
...– Implementation of minutiae feature extraction and matching [2] termed as Algorithm - A – Implementation of filterbank based feature extraction and matching [3] termed as Algorithm - B – Two commercial fingerprint recognition systems, termed as System - C and System - D(1)...
[...]