Fingerprint classification using a deep convolutional neural network

Pandya, Bhavesh; Cosma, Georgina; Alani, Ali A.; Taherkhani, Aboozar; Bharadi, Vinayak Ashok; McGinnity, TM

doi:10.1109/infoman.2018.8392815

Cited by 46 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…New developments in deep learning techniques have enhanced the performance of biometric systems across a wide range of biometric modalities, such as face recognition modality. We envisage that deep learning techniques [78][79][80] will also be potential tools for latent fingerprint matching. However, the use of deep learning algorithms may bring potential threats to biometric systems because of the vulnerabilities of those deep learning algorithms themselves.…”

Section: Discussionmentioning

confidence: 99%

Security and Accuracy of Fingerprint-Based Biometrics: A Review

et al. 2019

View full text Add to dashboard Cite

Biometric systems are increasingly replacing traditional password-and token-based authentication systems. Security and recognition accuracy are the two most important aspects to consider in designing a biometric system. In this paper, a comprehensive review is presented to shed light on the latest developments in the study of fingerprint-based biometrics covering these two aspects with a view to improving system security and recognition accuracy. Based on a thorough analysis and discussion, limitations of existing research work are outlined and suggestions for future work are provided. It is shown in the paper that researchers continue to face challenges in tackling the two most critical attacks to biometric systems, namely, attacks to the user interface and template databases. How to design proper countermeasures to thwart these attacks, thereby providing strong security and yet at the same time maintaining high recognition accuracy, is a hot research topic currently, as well as in the foreseeable future. Moreover, recognition accuracy under non-ideal conditions is more likely to be unsatisfactory and thus needs particular attention in biometric system design. Related challenges and current research trends are also outlined in this paper. recognition as an example. In the stage of enrollment, a user presents their finger to the fingerprint sensor and a fingerprint image is acquired by the sensor module. Certain features of the acquired fingerprint image are extracted, and further adapted or transformed to generate template data for the purpose of comparison in the verification stage. In the verification stage, the fingerprint image of a query is collected by the sensor module. The feature representations of the query fingerprint image go through the same process as in the enrollment stage, so as to obtain query data. The query data are then compared with the template data so that a matching outcome is attained.

show abstract

Section: Discussionmentioning

confidence: 99%

Security and Accuracy of Fingerprint-Based Biometrics: A Review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…According to Table 4 and Fig.8(a,b), all NN classifiers perform much better than the 5 non-NN classifiers in classification accuracy and model robustness, although the parameter scale of NN models is larger than non-NN models. The proposed model reaches 93% accuracy and outperforms Pandya B [15] and Peralta D [17]. The proposed model performs close to Nahar P [16].…”

Section: Comparation With Other Workmentioning

confidence: 66%

“…More importantly, the proposed model is the simplest, the easiest to train and test, and the least likely to encounter problems such as overfitting, gradient vanishing, etc. The total parameter number of the proposed model is only 816,261, far less than 31,013,477 of Pandya B's model [15], 136,921,989 of Nahar P's model [16], and 9,709,541 of Peralta D's model [17]. The results in Table4 show the deficiencies of classification accuracy and model robustness of two CNN structures proposed in [15] and [17], since their classification accuracy, AUC(ROC) and AUC(PR) are all smaller than the other two models.…”

Section: Comparation With Other Workmentioning

confidence: 97%

“…Pandya B [15] proposed a deep CNN structure with 3 CNN layers and 2 DNN layers. All fingerprint images are pre-processed by histogram equalization, Gabor filtering, thinning, etc., and then cropped to a specific size image, 350 × 233.…”

Section: Comparation With Other Workmentioning

confidence: 99%

“…Some of them have achieved good performance, while the network structures implemented in these works are intricate and require a lot of calculations. For example, some proposed CNN (Convolutional Neural Network) structures, like the Deep CNN model proposed by Pandya B [15], the ResNet50 in [16], and the CNN model mentioned by Peralta D [17], have numerous structural parameters and require considerable computational resources for training and testing. Neural network structures such as, RNN [8], Bayesian convolutional networks [14], etc.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Lightweight Convolutional Neural Network Based on Singularity ROI for Fingerprint Classification

Wen

Zhou

2020

IEEE Access

View full text Add to dashboard Cite

Fingerprint classification is a significant guarantee for efficient and accurate fingerprint recognition, especially when dealing with one-to-many fingerprint recognition. However, due to large intra-class variability, small inter-class variability, and noise, existing fingerprint classification algorithms still require further improvement in performance and efficiency. In this paper, a Lightweight CNN (Convolutional Neural Network) structure based on singularity ROI (region of interest) is proposed. The experimental results show that the accuracy on testing set of the proposed structure achieves 93%, which is far better than classic non-NN (neural network) classifiers, including RF(Random Forest), KNN (K-Nearest-Neighbor), LR (Logistic Regression), Linear SVM (Support Vector Machine), and RBF (Radial Basis Function) SVM. More momentously, compared with other three CNN structures published in recent years, the proposed structure achieves similar or even better performance with 1/12 to 1/38 parameter scale of other structures, which helps to proceed faster training and testing. Moreover, the proposed CNN model with fewer neurons can achieve better suppression of overfitting and robustness to noise.

show abstract

Enhanced fingerprint pattern classification: Integrating attention modules with lightweight deep learning models

Mukoya,

Rimiru,

Kimwele

2024

Engineering Reports

View full text Add to dashboard Cite

Large fingerprint databases can make the automated search process tedious and time‐consuming. Fingerprint pattern classification is a significant step in the identification system's complexity in terms of time and speed. Although several fingerprint algorithms have been developed for classification tasks, further improvements in performance and efficiency are still required. Most of the fingerprint algorithms use deep learning techniques. However, some deep learning techniques can be resource‐intensive and computationally expensive, while others can disregard the spatial relationships between the features used in classifying fingerprint patterns. This study proposes using lightweight deep learning models (i.e., MobileNet and EfficientNet‐B0) integrated with attention modules to classify fingerprint patterns. The two lightweight models are modified, yielding MobileNet+ and EfficientNet‐B0+ models. The lightweight deep learning models can help achieve optimal performance and reduce computational complexity. The attention modules focus on distinctive features for classification. Our proposed approach integrates four attention modules for fingerprint pattern classification into two lightweight deep learning models, that is, MobileNet+ and EfficientNet‐B0+. To evaluate our approach, we use two publicly available fingerprint datasets, that is, the NIST special database 301 dataset and the LivDet dataset. The evaluation results show that the EfficientNet‐B0+ model achieves the highest classification accuracy of 97% with only 854,086 training parameters. As a conclusion, we consider the training parameters small enough for the EfficientNet‐B0+ model to be deployed on low‐resource devices.

show abstract

Fingerprint classification using a deep convolutional neural network

Cited by 46 publications

References 10 publications

Security and Accuracy of Fingerprint-Based Biometrics: A Review

Security and Accuracy of Fingerprint-Based Biometrics: A Review

Lightweight Convolutional Neural Network Based on Singularity ROI for Fingerprint Classification

Enhanced fingerprint pattern classification: Integrating attention modules with lightweight deep learning models

Contact Info

Product

Resources

About