Extracting Fingerprint Features Using Autoencoder Networks for Gender Classification

Abstract

The fingerprint is an important biological feature of the human body, which contains abundant biometric information. At present, the academic exploration of fingerprint gender characteristics is generally at the level of understanding, and the standardization research is quite limited. A robust approach is presented in this article, Dense Dilated Convolution ResNet Autoencoder, to extract valid gender information from fingerprints. By replacing the normal convolution operations with the atrous convolution in the backbone, prior knowledge is provided to keep the edge details, and the global reception field can be extended. The results were explored from three aspects: (1) Efficiency of DDC-ResNet. We conducted experiments using a combination of 6 typical automatic feature extractors with 9 classifiers for a total of 54 combinations are evaluated in our dataset; the experimental results show that the combination of methods we used achieved an average accuracy of 96.5%, with a classification accuracy of 97.52% for males and 95.48% for females, which outperformed the other experimental combinations. (2) The effect of the finger. The results showed that the right ring finger was the most effective for finger classification by gender. (3) The effect of specific features. We used the Class Activating Mapping method to plot fingerprint concentration thermograms, which allowed us to infer that fingerprint epidermal texture features are related to gender. The results demonstrated that autoencoder networks are a powerful method for extracting gender-specific features to help hide the privacy information of the user’s gender contained in the fingerprint. Our experiments also identified three levels of features in fingerprints that are important for gender differentiation, including loops and whorls shape, bifurcations shape, and line shapes.

Enhancing Fingerprint Liveness Detection Accuracy Using Deep Learning: A Comprehensive Study and Novel Approach

“…The proposed methodology is superior to other deep learning convolution models, such as Xception, InceptionV3, VGG19, DenseNet121, and InceptionV3, with around 0.7% accuracy. Further investigations have been conducted concerning the employment of classifiers ( Figure 10 ), such as Random Forest (RF) [ 34 ], Linear Regression (LR) [ 35 ], KNN [ 36 ], SVM [ 37 ], Gaussian NB [ 37 ], Decision Tree [ 38 ], HMM [ 39 ], Autoencoder [ 40 ] and Support Vector Machine (SVM) [ 41 ]. Convolution layer five output from ResNet50 is converted into a 2048-dimensional array, which feeds all comparison classifiers.…”

Comparative Study of Fingerprint-Based Gender Identification

“…In [24], authors proposed a comparative study between AdaBoost, SVM with linear radial basis function (RBF) and polynomial kernel, KNN, J48, the Iterative Dichotomiser (ID3), linear discriminant analysis (LDA), and a CNN. Tey used six feature extraction methods: FFT, DWT, SVD, ResNet, VGG, and DDC-ResNet.…”

A Novel Image Compression Algorithm Based on Autoencoder for Biometric Template Protection Scheme

“…DNN-based approaches for image compression are proven to be very successful. Autoencoder comes under this approach (11,12) . https://www.indjst.org/…”