On restoration of degraded fingerprints

Joshi, Indu; Utkarsh, Ayush; Singh, Pravendra; Dantcheva, Antitza; Roy, Sumantra Dutta; Kalra, Prem Kumar

doi:10.1007/s11042-021-11863-3

Cited by 10 publications

(4 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This GAN was applied iteratively to enhance the fingerprint image until its quality achieved a satisfying result. In 2022, Joshi et al [26] proposed a GAN with an attention mechanism called "CRGAN" by inserting channel refinement units in the generator and the discriminator to restore degraded fingerprints. Recently, in 2023, Zhu et al [27] developed a GAN framework called "FingerGAN," which generates a fingerprint skeleton image as the output instead of an enhanced fingerprint image.…”

Section: Spatial Domainmentioning

confidence: 99%

Spectral Filter Predictor for Progressive Latent Fingerprint Restoration

Kriangkhajorn,

Horapong,

Areekul

2024

IEEE Access

View full text Add to dashboard Cite

Latent fingerprint restoration is one of the most challenging problems for fingerprint identification. According to the current next-generation identification (NGI) system fact sheet, the number of unsolved latent fingerprint cases is more than a million and is increasing daily. The current state-of-the-art algorithms utilize various deep-learning networks to restore latent fingerprints in the spatial domain. Unfortunately, these algorithms faced difficulty recovering genuine friction ridges from low-quality latent fingerprints with complex backgrounds and noise. Instead of using deep-learning models to restore latent fingerprints directly in the spatial domain, we used the deep-learning model to predict a frequency-domain filter for restoring each latent input partitioning block. We integrated this new filter predictor model within a progressive feedback framework. As a result, the proposed method can reveal genuine friction ridges from complex backgrounds, especially around very low-quality areas and singular point areas, which is crucial to the success of latent fingerprint identification. We benchmarked our proposed method against state-of-theart methods with four public latent fingerprint datasets. In addition, we used one commercial-of-the-shelf (COTS) and another open-source fingerprint matchers in our benchmark. The experiments showed that the proposed method outperformed current state-of-the-art methods in identification accuracy. Compared to the state-of-the-art methods using deep learning in the spatial domain, the proposed method achieved an average rank-1 identification accuracy improvement of 3.75% and 3.19% of four public datasets with the COTS and open-source fingerprint matchers, respectively. Finally, the execution code was made publicly available for non-commercial purposes at https://github.com/skconan/SFP-Progressive-Feedback-Latent-Fingerprint-Restoration.

show abstract

Section: Spatial Domainmentioning

confidence: 99%

Spectral Filter Predictor for Progressive Latent Fingerprint Restoration

Kriangkhajorn,

Horapong,

Areekul

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The generative adversial network (GAN) is the state-of-the-art image generation or enhancement techniques. The researchers in [ 112 ] recently demonstrated that the channel refinement-generative adversial network, which is one of the degraded fingerprint restoration methods, outperformed than the GAN and classical image processing enhancement.…”

Section: Image Acquisitionmentioning

confidence: 99%

“…For instance, in pre-processing, standard quality estimation mechanism and state-of-the-art image enhancement techniques can be practiced, while in feature extraction, deep and invariant feature representation can be employed [ 126 ]. For instance, in image enhancement and restoration, generative adversial network, which is the state-of-the-art method for image generative problems [ 112 ], can be employed. For invariant feature representation, ridge orientation pattern can be used as it will not be affected by sensor differences [ 7 ].…”

Section: Image Acquisitionmentioning

confidence: 99%

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

Mohamed-Abdul-Cader

Banks

Chandran

2023

Sensors

View full text Add to dashboard Cite

The fingerprint is a widely adopted biometric trait in forensic and civil applications. Fingerprint biometric systems have been investigated using contact prints and latent and contactless images which range from low to high resolution. While the imaging techniques are advancing with sensor variations, the input fingerprint images also vary. A general fingerprint recognition pipeline consists of a sensor module to acquire images, followed by feature representation, matching and decision modules. In the sensor module, the image quality of the biometric traits significantly affects the biometric system’s accuracy and performance. Imaging modality, such as contact and contactless, plays a key role in poor image quality, and therefore, paying attention to imaging modality is important to obtain better performance. Further, underlying physical principles and the working of the sensor can lead to their own forms of distortions during acquisition. There are certain challenges in each module of the fingerprint recognition pipeline, particularly sensors, image acquisition and feature representation. Present reviews in fingerprint systems only analyze the imaging techniques in fingerprint sensing that have existed for a decade. However, the latest emerging trends and recent advances in fingerprint sensing, image acquisition and their challenges have been left behind. Since the present reviews are either obsolete or restricted to a particular subset of the fingerprint systems, this work comprehensively analyzes the state of the art in the field of contact-based, contactless 2D and 3D fingerprint systems and their challenges in the aspects of sensors, image acquisition and interoperability. It outlines the open issues and challenges encountered in fingerprint systems, such as fingerprint performance, environmental factors, acceptability and interoperability, and alternate directions are proposed for a better fingerprint system.

show abstract

“…Fingerprints are among the most accurate and reliable biometric traits, which allows its applications in several domains, including digital transactions, criminal identification, and access control [3]- [7]. However, heavy noise is observed for fingerprints originating from a crime scene, commonly called latent fingerprints and fingerprints originating from individuals with poor skin condition around fingertips due to excessive manual work, such as fingerprints of the rural Indian population (see Figure 1).…”

Section: Introduction and Related Workmentioning

confidence: 99%