Hierarchical fusion for matching simultaneous latent fingerprint
06 Dec 2012-pp 377-382
TL;DR: An automated hierarchical fusion approach is proposed for fusing evidences from multiple latent impressions and IIITD simultaneous latent fingerprint database is prepared to drive further research in this area.
Abstract: Simultaneous latent fingerprints are a cluster of latent fingerprints that are concurrently deposited by the same person. Inherent challenges of latent fingerprints such as partial and smudgy ridge flow information, presence of background noise, and availability of less number of features makes it challenging to develop an automated system for simultaneous latent fingerprint matching. This research attempts to fill this gap by developing a fusion framework. The contribution of this paper is two-fold: (i) an automated hierarchical fusion approach is proposed for fusing evidences from multiple latent impressions and (ii) IIITD simultaneous latent fingerprint database is prepared to drive further research in this area. The proposed algorithm yields promising results on the simultaneous latent fingerprint database.
Citations
More filters
01 Jan 2021
TL;DR: Experiments show boosting-based Adaboost performs better with given feature set since no random selection of features is performed in boosting whereas bagging-based random decision forest classifier performs better in MDR/FDR trade-off with overall accuracy in the present application area.
Abstract: Latent fingerprints are unintentional fingermarks left at crime scenes. Latent fingerprint segmentation is to separate fingermarks, also known as ridge patterns, from a noisy background. The significant challenges in latent print segmentation are poor quality of images lifted from the crime scenes, overlapping prints, structured noise, unstructured background noise are difficult to analyze. Latent fingerprint classification based segmentation is performed using various techniques. Each image of the database is equally divided int local blocks of size 28 × 28. Further, features are extracted from each local block. Based on features, each block is classified into foreground, i.e., ridge pattern and background classes. Famously used ensemble techniques, bagging and boosting-based random decision forest and Adaboost ensemble models, respectively, are used as classifiers to compare the classification and segmentation accuracy and MDR/FDR as the performance metrics. Experiments show boosting-based Adaboost performs better with given feature set since no random selection of features is performed in boosting whereas bagging-based random decision forest classifier performs better in MDR/FDR trade-off with overall accuracy in the present application area.
8 citations
17 Dec 2015
TL;DR: This research creates a novel multi-surface latent fingerprint database and makes it publicly available for the research community to characterize the quality of latent fingerprints and compute the matching performance to analyze the effect of different surfaces.
Abstract: Latent fingerprints are lifted from multiple types of surfaces, which vary in material type, texture, color, and shape. These differences in the surfaces introduce significant intra-class variations in the lifted prints such as availability of partial print, background noise, and poor ridge structure quality. Due to these observed variations, the overall quality and the matching performance of latent fingerprints vary with respect to surface properties. Thus, characterizing the performance of latent fingerprints according to the surfaces they are lifted from is an important research problem that needs attention. In this research, we create a novel multi-surface latent fingerprint database and make it publicly available for the research community. The database consists of 551 latent fingerprints from 51 subjects lifted from eight different surfaces. Using existing algorithms, we characterize the quality of latent fingerprints and compute the matching performance to analyze the effect of different surfaces.
8 citations
Additional excerpts
...Database #Surfaces #Subjects #Images NIST SD-27 [5] NA 258 258 IIITD Latent [16] 2 15 1046 IIITD SLF [18] 1 30 1080 MOLF [21] 1 100 4400 Proposed 8 51 551...
[...]
TL;DR: This proposal proposes a fusion of fingerprint matching algorithms using a supervised classifier, which achieves higher identification rates than each lower-level algorithm and their fusion using traditional approaches for most of the rank values and reference databases.
Abstract: Automatic latent fingerprint identification is beneficial during forensic investigations. Usually, latent fingerprint identification algorithms are used to find a subset of similar fingerprints from those previously captured on databases, which are finally examined by latent examiners. Yet, the identification rate achieved by latent fingerprint identification algorithms is far from those obtained by latent examiners. One approach for improving identification rates is the fusion of the match scores computed with fingerprint matching algorithms using a supervised classification algorithm. This approach fuses the results provided by different lower-level algorithms to improve them. Thus, we propose a fusion of fingerprint matching algorithms using a supervised classifier. Our proposal starts with two different local matching algorithms. We substitute their global matching algorithms with another independent of the local matching, creating two lower-level algorithms for fingerprint matching. Then, we combine the output of these lower-level algorithms using a supervised classifier. Our proposal achieves higher identification rates than each lower-level algorithm and their fusion using traditional approaches for most of the rank values and reference databases. Moreover, our fusion algorithm reaches a Rank-1 identification rate of $$74.03\%$$
and $$71.32\%$$
matching the 258 samples in the NIST SD27 database against 29,257 and 100,000 references, the two largest reference databases employed in our experiments.
5 citations
Dissertation•
01 Feb 2017
TL;DR: This thesis improves the understanding and performance of automated matching systems for forensic latent fingerprints and fingerphoto images by designing an automated latent fingerprint segmentation algorithm that segments the fingerprint regions from background by distinguishing between ridge and non-ridge patterns.
Abstract: Fingerprint recognition has evolved over the decades, providing innumerable applications for improving the modern day security. Based on the method of capture, fingerprints can be classified into four variants: inked, live-scan, latent, and fingerphoto. Extensive research has been undertaken for inked and live-scanned fingerprints. However, research on latent fingerprints and fingerphoto matching is still in nascent stages. These two capture methodologies are semi-controlled or uncontrolled which pose significant variations in the feature space and therefore warrant further exploration. The key research challenges involved in building an automated system for latent fingerprint and fingerphoto matching are as follows: (i) lack of publicly available large scale datasets with diverse variations to motivate reproducible research, (ii) segmentation of foreground regions from the complex background surface, and (iii) lack of robust feature models to represent the noisy and partial finger ridge information. Currently, there are limited end-to-end automated systems for latent fingerprint and fingerphoto matching. This thesis primarily focuses in contributing towards building a completely automated “lights-out" matching system for these two fingerprint variants. There are four contributions ranging from creating large databases to designing algorithms for segmentation and feature extraction for these two fingerprint variants. First, we create two benchmark datasets with diverse acquisition methods: (i) Multi-sensor Optical and Latent Fingerprint (MOLF) dataset containing 19,200 fingerprint images with large intraclass and capture variations and (ii) IIIT-D SmartPhone FingerPhoto Dataset version 2 (ISPFD-v2) containing 16,800 images from 300 classes captured under different environmental setup. The second contribution is designing an automated latent fingerprint segmentation algorithm that segments the fingerprint regions from background by distinguishing between ridge and non-ridge patterns. Latent fingerprint segmentation is usually affected by the texture of the surface and smudges are introduced during lifting. The proposed learning-based algorithm is generalizable and can accommodate for unseen texture noises. Further, a novel Spectral Image Validation and Verification based metric is proposed to measure the effect of the segmentation algorithm. Third, a minutiae extraction algorithm is proposed as a major contribution towards the “lights-out" latent fingerprint matching. A novel group (or class) sparsity based l2,1 regularization method is proposed to improve the unsupervised features learnt using stacked autoencoders and Restricted Boltzmann Machines. Latent fingerprint minutiae extraction is then posed as a binary classification problem to classify patches as minutia or non-minutia. To the best of our knowledge, this is the first algorithm in literature for automated minutia extraction from latent fingerprints. The fourth contribution is towards fingerphoto recognition, in which a novel end-to-end fingerphoto matching algorithm is proposed that is invariant to the environmental factors such as background noise, illumination variation, and camera resolution. The ridge-valley pattern present in a fingerphoto in not as distinct as VII a fingerprint image, thus making minutia extraction highly noisy. The matching pipeline consists of a segmentation technique to extract the fingerphoto region of interest from varying background, followed by enhancement to neutralize the illumination imbalance and increase the ridge valley contrast. For feature extraction, a deep scattering network based representation is introduced. The resultant fingerphoto features are robust and invariant to environmental variations. By addressing these challenging problems, this thesis improves the understanding and performance of automated matching systems for forensic latent fingerprints and fingerphoto images.
5 citations
Cites background or methods from "Hierarchical fusion for matching si..."
...The camera setup is an improvised version of the setup created during the capture of the IIITD-SLF database [105]....
[...]
...∙ IIITD-SLF database [105] has 1080 latent impressions from 30 subjects (all 10 fingers) with mated exemplar prints....
[...]
...[105] created a public database for simultaneous latent fingerprint matching called IIITD Simultaneous Latent Fingerprint (IIITD-SLF) database having almost 360 simultaneous impressions from 60 classes....
[...]
...IIIT-D SLF [105] 180 420 X X X Simultaneous latent, 500 PPI slap....
[...]
...∙ Simultaneous latent fingerprint matching: The DB5 subset can be used for matching simultaneous latent fingerprints [104, 105]....
[...]
29 Apr 2016
TL;DR: Existing classification systems, including Henry, Vucetich, Battley, and NCIC classification systems are reviewed, and the challenges of classifying certain ambiguous fingerprints and interpreting latent prints are looked into.
Abstract: The usage of fingerprints is no longer limited to crime investigation. And automated fingerprint identification systems have been developed for a variety of applications. However, in law enforcement agency manual categorization and analysis are still an indispensible part of fingerprint operation mainly for the following two reasons: (1) Automated fingerprint classification and identification systems are far from perfection. They can help to expedite the identification process, but cannot completely replace human fingerprint experts in terms of identification accuracy; (2) Fingerprint classification can help speed up the automated searching process as fingerprint databases become overwhelmingly large. In this paper, we review existing classification systems, including Henry, Vucetich, Battley, and NCIC classification systems, and look into the challenges of classifying certain ambiguous fingerprints and interpreting latent prints. By reviewing literature and a representative case of fingerprint misidentification, we analyze the objective and subjective factors contributing to erroneous and inconsistent identification.
4 citations
Additional excerpts
...Matching latent with plain print [17] Fig....
[...]
References
More filters
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
01 Dec 2003
TL;DR: The main purpose has been to consider a large scale population, with statistical significance, in a real multimodal procedure, and including several sources of variability that can be found in real environments.
Abstract: The current need for large multimodal databases to evaluate automatic biometric recognition systems has motivated the development of the MCYT bimodal database. The main purpose has been to consider a large scale population, with statistical significance, in a real multimodal procedure, and including several sources of variability that can be found in real environments. The acquisition process, contents and availability of the single-session baseline corpus are fully described. Some experiments showing consistency of data through the different acquisition sites and assessing data quality are also presented.
676 citations
"Hierarchical fusion for matching si..." refers background in this paper
...To make the latent matching environment more challenging and realistic, 2000 optical fingerprints pertaining to 100 subjects from the MCYT database [13] are added to the gallery....
[...]
TL;DR: Experiments on three multibiometric databases indicate that the proposed fusion framework achieves consistently high performance compared to commonly used score fusion techniques based on score transformation and classification.
Abstract: Multibiometric systems fuse information from different sources to compensate for the limitations in performance of individual matchers. We propose a framework for the optimal combination of match scores that is based on the likelihood ratio test. The distributions of genuine and impostor match scores are modeled as finite Gaussian mixture model. The proposed fusion approach is general in its ability to handle 1) discrete values in biometric match score distributions, 2) arbitrary scales and distributions of match scores, 3) correlation between the scores of multiple matchers, and 4) sample quality of multiple biometric sources. Experiments on three multibiometric databases indicate that the proposed fusion framework achieves consistently high performance compared to commonly used score fusion techniques based on score transformation and classification.
538 citations
"Hierarchical fusion for matching si..." refers methods in this paper
...In this research, we have used (1) weighted sum rule [7] and (2) product of likelihood ratio (PLR) fusion [12]....
[...]
...The fused score for Algorithmj is computed using the weighted PLR fusion [12] as shown in equation 2....
[...]
Book•
27 Oct 1999
TL;DR: In this paper, the first step toward qualitative analysis of ridgeology has been taken towards a qualitative analysis in the field of Ridgeology, and the identification process of ridge identification has been described.
Abstract: Preface Introduction The First Step Toward Quantitative-Qualitative Analysis Ridgeology Revolution History of Friction Ridge Identification Primitive Knowledge Early Pioneers Scientific Researchers The Friction Ridge Medium Structure of Friction Skin Growth of Friction Skin The Identification Process Premises of Friction Ridge Identification Philosophy of Friction Ridge Identification Human Sight Methodology of Friction Ridge Identification Friction Ridge Analysis Friction Ridge Comparison Friction Ridge Evaluation Verification Poroscopy And Edgeoscopy Poroscopy Edgeoscopy Friction Ridge Analysis Report Ridgeology Study Key An Introduction To Palmar Flexion Crease Identification The Beginning Bibliography Glossary
377 citations
"Hierarchical fusion for matching si..." refers methods in this paper
...Simultaneous latent fingerprint examination is a complex application of ACE-V, where establishing simultaneity and utilizing multiple latent prints are main steps....
[...]
TL;DR: The experimental results indicate that singularity, ridge quality map, and ridge flow map are the most effective features in improving the matching accuracy.
Abstract: Latent fingerprint identification is of critical importance to law enforcement agencies in identifying suspects: Latent fingerprints are inadvertent impressions left by fingers on surfaces of objects. While tremendous progress has been made in plain and rolled fingerprint matching, latent fingerprint matching continues to be a difficult problem. Poor quality of ridge impressions, small finger area, and large nonlinear distortion are the main difficulties in latent fingerprint matching compared to plain or rolled fingerprint matching. We propose a system for matching latent fingerprints found at crime scenes to rolled fingerprints enrolled in law enforcement databases. In addition to minutiae, we also use extended features, including singularity, ridge quality map, ridge flow map, ridge wavelength map, and skeleton. We tested our system by matching 258 latents in the NIST SD27 database against a background database of 29,257 rolled fingerprints obtained by combining the NIST SD4, SD14, and SD27 databases. The minutiae-based baseline rank-1 identification rate of 34.9 percent was improved to 74 percent when extended features were used. In order to evaluate the relative importance of each extended feature, these features were incrementally used in the order of their cost in marking by latent experts. The experimental results indicate that singularity, ridge quality map, and ridge flow map are the most effective features in improving the matching accuracy.
292 citations
"Hierarchical fusion for matching si..." refers background or methods in this paper
...Jain and Feng [11] provided a comprehensive analysis of latent fingerprint matching....
[...]
...Dusted latent fingerprints are usually lifted from the surface using tapes, stored in cards, and scanned using optical scanners....
[...]