Automated Latent Fingerprint Recognition

Cao, Kai; Jain, Anil K.

doi:10.1109/tpami.2018.2818162

Cited by 166 publications

(136 citation statements)

References 38 publications

Supporting

Mentioning

135

Contrasting

Unclassified

Order By: Relevance

“…As an addendum, deep networks have also been used to improve specific sub-modules of fingerprint recognition systems such as segmentation [30], [31], [32], [33], orientation field estimation [34], [35], [36], minutiae extraction [37], [38], [39], and minutiae descriptor extraction [40]. However, these works all still operate within the conventional paradigm of extracting an unordered, variable length set of minutiae for fingerprint matching.…”

Section: Prior Workmentioning

confidence: 99%

Learning a Fixed-Length Fingerprint Representation

Engelsma

Cao²,

Jain

2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

108

View full text Add to dashboard Cite

We present DeepPrint, a deep network, which learns to extract fixed-length fingerprint representations of only 200 bytes. DeepPrint incorporates fingerprint domain knowledge, including alignment and minutiae detection, into the deep network architecture to maximize the discriminative power of its representation. The compact, DeepPrint representation has several advantages over the prevailing variable length minutiae representation which (i) requires computationally expensive graph matching techniques, (ii) is difficult to secure using strong encryption schemes (e.g. homomorphic encryption), and (iii) has low discriminative power in poor quality fingerprints where minutiae extraction is unreliable. We benchmark DeepPrint against two top performing COTS SDKs (Verifinger and Innovatrics) from the NIST and FVC evaluations. Coupled with a re-ranking scheme, the DeepPrint rank-1 search accuracy on the NIST SD4 dataset against a gallery of 1.1 million fingerprints is comparable to the top COTS matcher, but it is significantly faster (DeepPrint: 98.80% in 0.3 seconds vs. COTS A: 98.85% in 27 seconds). To the best of our knowledge, the DeepPrint representation is the most compact and discriminative fixed-length fingerprint representation reported in the academic literature.

show abstract

Section: Prior Workmentioning

confidence: 99%

Learning a Fixed-Length Fingerprint Representation

Engelsma

Cao²,

Jain

2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

108

View full text Add to dashboard Cite

show abstract

“…Cao and Jain [31] proposed the use of minutiae descriptors that are learned via a ConvNet together with minutiae and texture information to improve the latent fingerprint recognition. They performed score level fusion of their proposed algorithm with commercial minutiae-based matchers to improve the rank identification accuracies.…”

Section: Related Workmentioning

confidence: 99%

Improving automated latent fingerprint identification using extended minutia types

et al. 2019

View full text Add to dashboard Cite

Latent fingerprints are usually processed with Automated Fingerprint Identification Systems (AFIS) by law enforcement agencies to narrow down possible suspects from a criminal database. AFIS do not commonly use all discriminatory features available in fingerprints but typically use only some types of features automatically extracted by a feature extraction algorithm. In this work, we explore ways to improve rank identification accuracies of AFIS when only a partial latent fingerprint is available. Towards solving this challenge, we propose a method that exploits extended fingerprint features (unusual/rare minutiae) not commonly considered in AFIS. This new method can be combined with any existing minutiae-based matcher. We first compute a similarity score based on least squares between latent and tenprint minutiae points, with rare minutiae features as reference points. Then the similarity score of the reference minutiae-based matcher at hand is modified based on a fitting error from the least square similarity stage. We use a realistic forensic fingerprint casework database in our experiments which contains rare minutiae features obtained from Guardia Civil, the Spanish law enforcement agency. Experiments are conducted using three * Corresponding author Email addresses: ram.krish@dcu.ie (Ram P. Krish), julian.fierrez@uam.es (Julian Fierrez), daniel.ramos@uam.es (Daniel Ramos), feralo@hh.se (Fernando Alonso-Fernandez), josef.bigun@hh.se (Josef Bigun) 2018. This manuscript version is made available under the CC-BY-NC-ND 4.0 license. http://creativecommons.org/licenses/by-nc-nd/4.0/ The final version is available online at: https://doi.minutiae-based matchers as a reference, namely: NIST-Bozorth3, VeriFinger-SDK and MCC-SDK. We report significant improvements in the rank identification accuracies when these minutiae matchers are augmented with our proposed algorithm based on rare minutiae features.

show abstract

“…Salient descriptors are needed to establish minutiae correspondences and compute the similarity between a latent and reference prints. Instead of specifying the descriptor in an ad hoc manner, Cao and Jain [4] trained ConvNets to learn Figure 5. Examples of training fingerprint patches.…”

Section: Descriptors For Virtual Minutiaementioning

confidence: 99%

“…Figure 6. Four different patch types used in [4] for descriptor extraction. Patch types in (a)-(c) were determined to be the best combination in terms of identification accuracy.…”

Section: Descriptors For Virtual Minutiaementioning

confidence: 99%

“…Cao and Jain [4] proposed a virtual minutiae based approach for latent fingerprint recognition, where the virtual minutiae locations are determined by a raster scan with a stride of 16 pixels; the associated descriptors are obtained by three convolutional neural networks. Experimental results on two latent databases, NIST SD27 and WVU, showed that the recognition performance of virtual minutiae based "texture template" when fused with two different true minutiae templates boosts the rank-1 accuracy from 58.5% to 64.7% against 100K reference print gallery for NIST SD27 [4]. However, the virtual minutiae feature extractor and matcher are quite slow.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Latent Fingerprint Recognition: Role of Texture Template

Cao

Jain

2018

2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS)

Self Cite

View full text Add to dashboard Cite

We propose a texture template approach, consisting of a set of virtual minutiae, to improve the overall latent fingerprint recognition accuracy. To compensate for the lack of sufficient number of minutiae in poor quality latent prints, we generate a set of virtual minutiae. However, due to a large number of these regularly placed virtual minutiae, texture based template matching has a large computational requirement compared to matching true minutiae templates. To improve both the accuracy and efficiency of the texture template matching, we investigate: i) both original and enhanced fingerprint patches for training convolutional neural networks (ConvNets) to improve the distinctiveness of descriptors associated with each virtual minutiae, ii) smaller patches around virtual minutiae and a fast ConvNet architecture to speed up descriptor extraction, iii) reduce the descriptor length, iv) a modified hierarchical graph matching strategy to improve the matching speed, and v) extraction of multiple texture templates to boost the performance. Experiments on NIST SD27 latent database show that the above strategies can improve the matching speed from 11 ms (24 threads) per comparison (between a latent and a reference print) to only 7.7 ms (single thread) per comparison while improving the rank-1 accuracy by 8.9% against 10K gallery.

show abstract

Automated Latent Fingerprint Recognition

Cited by 166 publications

References 38 publications

Learning a Fixed-Length Fingerprint Representation

Learning a Fixed-Length Fingerprint Representation

Improving automated latent fingerprint identification using extended minutia types

Latent Fingerprint Recognition: Role of Texture Template

Contact Info

Product

Resources

About