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 7 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

See 1 more Smart Citation

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

Section: Image Acquisitionmentioning

confidence: 99%

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

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%

Context-Aware Restoration of Noisy Fingerprints

et al. 2022

Self Cite

View full text Add to dashboard Cite

Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data

Margaryan,

Seibold,

Joshi

et al. 2023

Medical Imaging and Computer-Aided Diagnosis

Self Cite

View full text Add to dashboard Cite

Data augmentation is a valuable tool for the design of deep learning systems to overcome data limitations and stabilize the training process. Especially in the medical domain, where the collection of large-scale data sets is challenging and expensive due to limited access to patient data, relevant environments, as well as strict regulations, community-curated large-scale public datasets, pretrained models, and advanced data augmentation methods are the main factors for developing reliable systems to improve patient care. However, for the development of medical acoustic sensing systems, an emerging field of research, the community lacks large-scale publicly available data sets and pretrained models. To address the problem of limited data, we propose a conditional generative adversarial neural network-based augmentation method which is able to synthesize mel spectrograms from a learned data distribution of a source data set. In contrast to previously proposed fully convolutional models, the proposed model implements residual Squeeze and Excitation modules in the generator architecture. We show that our method outperforms all classical audio augmentation techniques and previously published generative methods in terms of generated sample quality and a performance improvement of 2.84% of Macro F1-Score for a classifier trained on the augmented data set, an enhancement of 1.14% in relation to previous work. By analyzing the correlation of intermediate feature spaces, we show that the residual Squeeze and Excitation modules help the model to reduce redundancy in the latent features. Therefore, the proposed model advances the state-of-the-art in the augmentation of clinical audio data and improves the data bottleneck for the design of clinical acoustic sensing systems.

show abstract

On restoration of degraded fingerprints

Cited by 7 publications

References 58 publications

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

Context-Aware Restoration of Noisy Fingerprints

Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data

Contact Info

Product

Resources

About