De-convolutional auto-encoder for enhancement of fingerprint samples

Fingerprint classification is one of the most common approaches to accelerate the identification in large databases of fingerprints. Fingerprints are grouped into disjoint classes, so that an input fingerprint is compared only with those belonging to the predicted class, reducing the penetration rate of the search. The classification procedure usually starts by the extraction of features from the fingerprint image, frequently based on visual characteristics. In this work, we propose an approach to fingerprint classification using convolutional neural networks, which avoid the necessity of an explicit feature extraction process by incorporating the image processing within the training of the classifier. Furthermore, such an approach is able to predict a class even for low-quality fingerprints that are rejected by commonly used algorithms, such as FingerCode. The study gives special importance to the robustness of the classification for different impressions of the same fingerprint, aiming to minimize the penetration in the database. In our experiments, convolutional neural networks yielded better accuracy and penetration rate than state-of-the-art classifiers based on explicit feature extraction. The tested networks also improved on the runtime, as a result of the joint optimization of both feature extraction and classification. wileyonlinelibrary.com/journal/int

show abstract

“…Finally, Ref. describes a deep deconvolutional neural network to enhance the quality of fingerprint images before minutiae extraction.…”

Section: Introductionmentioning

confidence: 99%

On the use of convolutional neural networks for robust classification of multiple fingerprint captures

Peralta

Triguero

García

et al. 2017

Int. J. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Kumar and Velusamy [66] proposed to learn dictionaries of orientation patches for later use during enhancement. Schuch et al [67] proposed to train and apply deconvolutional auto-encoders for fingerprint enhancement. Khan and Khan [68] proposed to use a data driven approach to reassemble a fingerprint from its decomposition into directional images.…”

Section: Methods Of Image Enhancementsmentioning

confidence: 99%

“…Schuch et al . [67] proposed to train and apply de‐convolutional auto‐encoders for fingerprint enhancement. Khan and Khan [68] proposed to use a data driven approach to reassemble a fingerprint from its decomposition into directional images.…”

Section: Methods Of Image Enhancementsmentioning

confidence: 99%

Survey on the impact of fingerprint image enhancement

Schuch¹,

Schulz²,

Busch³

2017

IET biom.

Self Cite

View full text Add to dashboard Cite

The performance of fingerprint comparison algorithms depends on the reliability and accuracy of the features extracted from the fingerprints. The accuracy of the feature extraction algorithms is assumed to depend on the quality of the fingerprint images. Especially, low-quality images can be challenging for feature extraction algorithms. Image enhancement may allow to extract features more accurately. There is a lack of extensive and quantitative evaluation of image enhancement methods. This study investigates the impact of seven typical image enhancement methods on biometric sample quality and on biometric performance. The interrelation of image quality and biometric performance is investigated on 14 datasets. Biometric quality measures are estimated based on image quality metrics NFIQ1 and NFIQ2.0. Biometric performance is tested using MINDTCT and FingerJetFX for feature extraction and BOZORTH3 for biometric comparison. This work shows that the biometric performance can be improved by image enhancement. The significance of improvements depends on both the quality of the datasets and the feature extraction. Thus, there is no single best improvement algorithm. A correlation of changes in scores and image qualities can only be found on the level of entire datasets. No significant correlation can be found for single biometric comparisons.

show abstract

“…Most recent work similar to the proposed approach is Schuch et al [32], who used a convolutional autoencoder for inked and sensor-scan fingerprints ridge enhancement. Their network had a rather simple architecture and was not evaluated in challenging latent fingerprint recognition settings.…”

Section: Related Workmentioning

confidence: 99%

Generative convolutional networks for latent fingerprint reconstruction

Svoboda

Monti

Bronstein

2017

2017 IEEE International Joint Conference on Biometrics (IJCB)

View full text Add to dashboard Cite

Performance of fingerprint recognition depends heavily on the extraction of minutiae points. Enhancement of the fingerprint ridge pattern is thus an essential pre-processing step that noticeably reduces false positive and negative detection rates. A particularly challenging setting is when the fingerprint images are corrupted or partially missing. In this work, we apply generative convolutional networks to denoise visible minutiae and predict the missing parts of the ridge pattern. The proposed enhancement approach is tested as a pre-processing step in combination with several standard feature extraction methods such as MINDTCT, followed by biometric comparison using MCC and BO-ZORTH3. We evaluate our method on several publicly available latent fingerprint datasets captured using different sensors.

show abstract

De-convolutional auto-encoder for enhancement of fingerprint samples

Cited by 17 publications

References 15 publications

On the use of convolutional neural networks for robust classification of multiple fingerprint captures

On the use of convolutional neural networks for robust classification of multiple fingerprint captures

Survey on the impact of fingerprint image enhancement

Generative convolutional networks for latent fingerprint reconstruction

Contact Info

Product

Resources

About