Feature extraction, recognition, and matching of damaged fingerprint: Application of deep learning network

Li, Hongbin

doi:10.1002/cpe.6057

Cited by 11 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the most common metrics are used to evaluate the performance of fingerprint matching systems [ 15 ]. First, it is necessary to define the concepts that allow computing of those metrics.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Fingerprint Recognition in Forensic Scenarios

Martins,

Silva,

Bernardino

2024

Sensors

View full text Add to dashboard Cite

Fingerprints are unique patterns used as biometric keys because they allow an individual to be unambiguously identified, making their application in the forensic field a common practice. The design of a system that can match the details of different images is still an open problem, especially when applied to large databases or, to real-time applications in forensic scenarios using mobile devices. Fingerprints collected at a crime scene are often manually processed to find those that are relevant to solving the crime. This work proposes an efficient methodology that can be applied in real time to reduce the manual work in crime scene investigations that consumes time and human resources. The proposed methodology includes four steps: (i) image pre-processing using oriented Gabor filters; (ii) the extraction of minutiae using a variant of the Crossing Numbers method which include a novel ROI definition through convex hull and erosion followed by replacing two or more very close minutiae with an average minutiae; (iii) the creation of a model that represents each minutia through the characteristics of a set of polygons including neighboring minutiae; (iv) the individual search of a match for each minutia in different images using metrics on the absolute and relative errors. While in the literature most methodologies look to validate the entire fingerprint model, connecting the minutiae or using minutiae triplets, we validate each minutia individually using n-vertex polygons whose vertices are neighbor minutiae that surround the reference. Our method also reveals robustness against false minutiae since several polygons are used to represent the same minutia, there is a possibility that even if there are false minutia, the true polygon is present and identified; in addition, our method is immune to rotations and translations. The results show that the proposed methodology can be applied in real time in standard hardware implementation, with images of arbitrary orientations.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Li [ 15 ] proposes the use of a CNN to extract features and match noisy fingerprints. The proposed method achieved FMR 1.54% and FNMR 1.46% in the NIST DB4 database and was compared with a traditional method (based on coordinates and orientation of minutiae) that produced 28.82% and 28.78%, respectively.…”

Section: Related Workmentioning

confidence: 99%

Fingerprint Recognition in Forensic Scenarios

Martins,

Silva,

Bernardino

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Another interesting study by Reference 25 used a combination of features from each finger to improve gender recognition accuracy. Study for recognition of fingerprints that are damaged conducted by Reference 26 employed the use of an improved Convolutional Neural Network (CNN) to realize better recognition accuracy than traditional CNN. All these studies used deep learning models for their classification tasks.…”

Section: Related Workmentioning

confidence: 99%

Accelerating deep learning inference via layer truncation and transfer learning for fingerprint classification

Mukoya

Rimiru

Kimwele

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

Biometric systems have been used extensively in the identification and verification of persons. Fingerprint biometrics stands out as the most effective due to their characteristics of Permanence, uniqueness, ergonomics, throughput, low cost, and lifelong usability. By reducing the number of comparisons, biometric recognition systems can effectively deal with large-scale databases. Fingerprint classification is an important task used to reduce the number of comparisons by dividing fingerprints into classes.Deep learning models have demonstrated impressive classification performance in fingerprint classification tasks. The high-level features of deep learning models can affect the transfer learning in deep learning models. Furthermore, the high-level features involve high computational costs that can render difficulty in the deployment of the applications. This work proposes an improved system for fingerprint classification through the truncation of layers and transfer learning. Our approach modifies the ResNet50 model to improve its network inference speed and performance in fingerprint classification by removing some deep convolutional layers. We then finetune the modified model and train it using a fingerprint dataset. The results show that the finetuned modified model improves classification accuracy at a reduced computational cost. At only 5.1M parameters, our model obtained a classification accuracy of 93.3% and precision of 93.4% performing better than previous studies based on its size-performance ratio.

show abstract

“…The dividing of an image into tiny blocks benefits in extracting the feature motifs. Where kernel integrates with the images using a common set of weights by multiplying elements with the target elements 18 . Convolution layer can be showed:

{f}_l^k\left(\ p,q\right)=\sum \limits_c\sum \limits_{x,y}{i}_c\ \left(x,y\right)\cdot {e}_l^k\left(u,v\right)

…”

Section: Deep Learning Architecturesmentioning

confidence: 99%

“…Where kernel integrates with the images using a common set of weights by multiplying elements with the target elements. 18 Convolution layer can be showed:…”

Section: Convolutional Layermentioning

confidence: 99%

A robust optimized convolutional neural network model for human activity recognition using sensing devices

Ata

Francies

2022

Concurrency and Computation

View full text Add to dashboard Cite

Human activity recognition has become an expansive field of interest in recent years, both in academic and industrial research. Human Activity recognition (HAR) is concerning the prediction of person's movement or action such as walking, standing, sitting, up and downstairs, etc. Convolutional neural network (CNN) is a key component with deep learning. The main objective of this study is to design and implement an activity recognition algorithm in the state of the art of deep learning systems which accomplish superlative performance to detect human activities. Accordingly, an extensive comparison has been developed between different deep learning algorithms such as classical (CNN) models and Recurrent Neural Network (RNN) models with respect to the major human activities. Furthermore, a robust (CNN) deep learning model has been built up and proposed in order to enhance the recognition precision of human activities. This proposed model uses raw data acquired from a set of inertial sensor and exploring numerous human achas been built up and proposedtivities; sitting, standing, jogging, walking, and etc. Experimental results show that the precision of the proposed deep structure has achieved 97.5% with respect to the NAdam optimizer which would be considered as the most effectively recognizer compared to other deep learning architectures.

show abstract

Feature extraction, recognition, and matching of damaged fingerprint: Application of deep learning network

Cited by 11 publications

References 13 publications

Fingerprint Recognition in Forensic Scenarios

Fingerprint Recognition in Forensic Scenarios

Accelerating deep learning inference via layer truncation and transfer learning for fingerprint classification

A robust optimized convolutional neural network model for human activity recognition using sensing devices

Contact Info

Product

Resources

About