Fingerprint frequency normalisation and enhancement using two‐dimensional short‐time Fourier transform analysis

Ghafoor, Mubeen; Taj, Imtiaz A.; Jafri, M.N.

doi:10.1049/iet-cvi.2016.0005

Cited by 14 publications

(10 citation statements)

References 28 publications

(90 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reliably extract minutia features, fingerprint images are enhanced prior to feature extraction. The enhancement stage is intended to improve the image quality by performing different operations such as removing distortions, increasing contrast between ridges and valleys and connecting false broken points of ridges [35][36][37]. Minutia features are then extracted from the skeletonised image after performing fingerprint enhancement and minutiae post-processing [38].…”

Section: Proposed Methodology For Fi Processmentioning

confidence: 99%

Efficient fingerprint matching using GPU

Ghafoor

Iqbal

Tariq

et al. 2018

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Section: Proposed Methodology For Fi Processmentioning

confidence: 99%

Efficient fingerprint matching using GPU

Ghafoor

Iqbal

Tariq

et al. 2018

IET Image Processing

Self Cite

View full text Add to dashboard Cite

“…Enhancement filters which are usually Gabor filters or other contextual filters, need to adapt their orientation and width according to local ridge orientation and frequency respectively. Filtering can be applied in spatial domain [8,16,19,21,35,44] or frequency domain [9,17]. In spatial domain, filtering is applied pixel wise, where filter orientation and width are adapted to ridge pattern in a small area centred at a pixel (x, y).…”

Section: Gradient Based Techniquesmentioning

confidence: 99%

Palmprint enhancement network (PEN) for robust identification

Mehmood

Taj

Ghafoor

2023

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Despite being reliable, palmprints have not received as much attention as other biometrics such as fingerprints, face or iris. Amount of information provided by high resolution palmprints and the fact that they have huge forensic value makes them a preferred biometric choice for large scale identification systems. In palmprints, extraction of reliable features for identification is still a challenging task especially because most of palmprints found in the real world, e.g., in crime scenes, are of poor quality. This makes palmprint enhancement a crucial pre cursor to identification. Errors during enhancement result in extraction of un-reliable features which deteriorate identification accuracy. Recent works in palmprints have focused more on matching algorithms and limited novelty has been introduced in enhancement. Enhancement techniques used on high resolution palmprints recently are either borrowed from fingerprint techniques or are built on the high-risk assumption that palm ridge pattern is stationary or smooth in a local area. Large size and abruptly changing ridge pattern of palmprints dictates the need for a more robust enhancement scheme. This paper proposes a novel deep learning based high resolution palmprint enhancement approach that is able to process large areas of palmprint without making the assumption that underlying ridge pattern is stationary. We have tested proposed enhancement approach on a renowned high resolution palmprint dataset which shows that proposed technique performs favourably in comparison to state of the art.

show abstract

“…Since the ridge/valley pattern of palmprints is very similar to the structure of fingerprint images, the processing and enhancement process for both the biometrics is very similar, as well. Palmprint preprocessing and enhancement typically consist of region-ofinterest (ROI) segmentation, enhancement based on local ridge frequencies and orientations, followed by binarisation and thinning [12][13][14]. ROI segmentation is performed to extract the required palmprint region from the background and discard any irrelevant information.…”

Section: Palmprint Preprocessing and Enhancementmentioning

confidence: 99%

Robust palmprint identification using efficient enhancement and two‐stage matching technique

et al. 2020

Self Cite

View full text Add to dashboard Cite

Palmprint‐based human authentication has shown great potential for civil, forensic, and corporate security applications in recent years. Palmprint recognition systems suffer because of large palmprint sizes and the presence of a large number of creases and erroneous minutiae that make the enhancement and matching phases a challenge. In this study, a novel approach is presented based on efficient enhancement and a two‐stage matching technique that demonstrates highly accurate identification results. The enhancement approach extracts minutia features from high‐quality regions based on local ridge characteristics. The selected minutiae are then matched using a two‐stage local and global minutiae neighbour‐based matching technique. To demonstrate the performance of the proposed technique, comparisons with open‐source algorithms are made based on equal error rate and detection error trade‐off graph. The results confirm the efficacy of proposed palmprint enhancement and identification technique.

show abstract

Fingerprint frequency normalisation and enhancement using two‐dimensional short‐time Fourier transform analysis

Cited by 14 publications

References 28 publications

Efficient fingerprint matching using GPU

Efficient fingerprint matching using GPU

Palmprint enhancement network (PEN) for robust identification

Robust palmprint identification using efficient enhancement and two‐stage matching technique

Contact Info

Product

Resources

About