Low-quality fingerprint recognition using a limited ellipse-band-based matching method

He, Zaixing; Zhao, Xinyue; Zhang, Shuyou

doi:10.1364/josaa.32.001171

Cited by 11 publications

(13 citation statements)

References 24 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zaixing et al [15] developed a limited ellipse-band-based matching algorithm for fingerprint recognition. The method utilized the Fourier-Mellin transformation method and ellipse band on the frequency amplitude to suppress noise.…”

Section: Related Workmentioning

confidence: 99%

Cycle-consistent generative adversarial neural networks based low quality fingerprint enhancement

Karabulut

Tertychnyi

Arslan

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

Distortions such as dryness, wetness, blurriness, physical damages and presence of dots in fingerprints are a detriment to a good analysis of them. Even though fingerprint image enhancement is possible through physical solutions such as removing excess grace on the fingerprint or recapturing the fingerprint after some time, these solutions are usually not user-friendly and time consuming. In some cases, the enhancements may not be possible if the cause of the distortion is permanent. In this paper, we are proposing an unpaired image-to-image translation using cycle-consistent adversarial networks for translating images from distorted domain to undistorted domain, namely, dry to not-dry, wet to not-wet, dotted to not-dotted, damaged to not-damaged, blurred to not-blurred. We use a database of low quality fingerprint images containing 11541 samples with dryness, wetness, blurriness, damages and dotted distortions. The database has been prepared by real data from VISA application centres and have been provided for this research by GEYCE Biometrics. For the evaluation of the proposed enhancement technique, we use VGG16 based convolutional neural network to assess the percentage of enhanced fingerprint images which are labelled correctly as undistorted. The proposed quality enhancement technique has achieved the maximum quality improvement for wetness fingerprints in which 94% of the enhanced wet fingerprints were detected as undistorted.

show abstract

Section: Related Workmentioning

confidence: 99%

Cycle-consistent generative adversarial neural networks based low quality fingerprint enhancement

Karabulut

Tertychnyi

Arslan

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…In [24], a recognition algorithm using a limited ellipse‐band‐based matching method was introduced. This method used the Fourier–Mellin transformation method.…”

Section: Related Workmentioning

confidence: 99%

Low‐quality fingerprint classification using deep neural network

2018

View full text Add to dashboard Cite

Fingerprint recognition systems mainly use minutiae points information. As shown in many previous research works, fingerprint images do not always have good quality to be used by automatic fingerprint recognition systems. To tackle this challenge, in this work, the authors are focusing on very low-quality fingerprint images, which contain several well-known distortions such as dryness, wetness, physical damage, presence of dots, and blurriness. They develop an efficient, with high accuracy, deep neural network algorithm, which recognises such low-quality fingerprints. The experimental results have been obtained from the real low-quality fingerprint database, and the achieved results show the high performance and robustness of the introduced deep network technique. The VGG16-based deep network achieves the highest performance of 93% for dry and the lowest performance of 84% for blurred fingerprint classes.

show abstract

“…2) The final encoded list E for a given candidate fingerprint is a combination of all individual encoded minutiae m' j , which have been encoded based on n-nearest neighbours as given by (7). This encoded list can be represented as…”

Section: Feature Encodingmentioning

confidence: 99%

“…Most widely used fingerprint identification (FI) techniques rely on these minutia features because these are very accurate and they support latent fingerprint matching [4,5]. Although many different minutia-based encoding and matching techniques have been proposed over the years, the basic methodology remains the same, and that is each minutia is encoded and matched based on the relative distances and angles with neighbouring minutiae [6,7]. Jiang and Yau [8] proposed a rotation and translation invariant encoding and matching technique based on minutia-triplet structure.…”

Section: Introductionmentioning

confidence: 99%