Fingerprint Enhancement Based on Tensor of Wavelet Subbands for Classification

Ngoc Tuyen Le,Jing-Wein Wang,Duc Huy Le,Chih-Chiang Wang,Tu N Nguyen

doi:10.1109/access.2020.2964035

Ngoc Tuyen Le, Jing-Wein Wang + Show 3 more

Open Access

https://doi.org/10.1109/access.2020.2964035

Copy DOI

Abstract

Fingerprint image enhancement is a key aspect of an automated fingerprint identification system. This paper describes an effective algorithm based on a novel lighting compensation scheme. The scheme involves the use of adaptive higher-order singular value decomposition on a tensor of wavelet subbands of a fingerprint (AHTWF) image to enhance the quality of the image. The algorithm consists of three stages. The first stage is the decomposition of an input fingerprint image of size <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2M\times 2N$ </tex-math></inline-formula> into four subbands at the first level by applying a two-dimensional discrete wavelet transform. In the second stage, we construct a tensor in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathbb {R}^{M\times N\times 4}$ </tex-math></inline-formula> space. The tensor contains four wavelet subbands that serve as four frontal planes. Furthermore, the tensor is decomposed through higher-order singular value decomposition to separate the fingerprint’s wavelet subbands into detailed individual components. In the third stage, a compensated image is produced by adaptively obtaining the compensation coefficient for each frontal plane of the tensor-based on the reference Gaussian template. The experimental results indicated that the quality of the AHTWF image was higher than that of the original image. The proposed algorithm not only improves the clarity and continuity of ridge structures but also removes the background and blurred regions of a fingerprint image. Therefore, this algorithm can achieve higher fingerprint classification accuracy than related methods can.

Highlights

Fingerprint classification is a required preliminary step in automated fingerprint identification systems (AFIS), which are increasingly used in law enforcement agencies to identify criminals as well as in commercial, civilian, philological, and financial domains
EXPERIMENTAL RESULTS AND DISCUSSION The higher-order SVD (HOSVD) decomposes the tensor into four main components includes the core tensor and three types of inverse factors
By constructing the tensor of wavelet subbands of the fingerprint image and using the HOSVD to decompose it into more detail components, we can find more information and the relation of wavelet subbands in three directions

Summary

Introduction

Fingerprint classification is a required preliminary step in automated fingerprint identification systems (AFIS), which are increasingly used in law enforcement agencies to identify criminals as well as in commercial, civilian, philological, and financial domains. Fingerprint classification considerably reduces the identification time of an AFIS, for which accuracy and speed are critical. Most fingerprint classification algorithms are used to classify fingerprints into four or five classes, as described by Henry [1]. In [2], fingerprints were classified into seven classes according to hierarchical singular point detection and traced orientation flow. In this method, fingerprints were divided into seven classes by separating Whorls into three types: Eddy (E), S-type (S), and Whorl. Most fingerprint classification methods are based on one or more of the following features: image orientation, ridgeline

Objectives

Results

Conclusion