An Innovative Scheme For Effectual Fingerprint Data Compression Using Bezier Curve Representations

by   Vani Perumal, et al.

Naturally, with the mounting application of biometric systems, there arises a difficulty in storing and handling those acquired biometric data. Fingerprint recognition has been recognized as one of the most mature and established technique among all the biometrics systems. In recent times, with fingerprint recognition receiving increasingly more attention the amount of fingerprints collected has been constantly creating enormous problems in storage and transmission. Henceforth, the compression of fingerprints has emerged as an indispensable step in automated fingerprint recognition systems. Several researchers have presented approaches for fingerprint image compression. In this paper, we propose a novel and efficient scheme for fingerprint image compression. The presented scheme utilizes the Bezier curve representations for effective compression of fingerprint images. Initially, the ridges present in the fingerprint image are extracted along with their coordinate values using the approach presented. Subsequently, the control points are determined for all the ridges by visualizing each ridge as a Bezier curve. The control points of all the ridges determined are stored and are used to represent the fingerprint image. When needed, the fingerprint image is reconstructed from the stored control points using Bezier curves. The quality of the reconstructed fingerprint is determined by a formal evaluation. The proposed scheme achieves considerable memory reduction in storing the fingerprint.




An Efficient Automatic Attendance System Using Fingerprint Reconstruction Technique

Biometric time and attendance system is one of the most successful appli...

CuCoTrack: Cuckoo Filter Based Connection Tracking

This paper introduces CuCoTrack, a cuckoo hash based data structure desi...

SynCoLFinGer: Synthetic Contactless Fingerprint Generator

We present the first method for synthetic generation of contactless fing...

Parallel Stroked Multi Line: a model-based method for compressing large fingerprint databases

With increasing usage of fingerprints as an important biometric data, th...

An Effective Method for Fingerprint Classification

This paper presents an effective method for fingerprint classification u...

Perfect Fingerprint Orientation Fields by Locally Adaptive Global Models

Fingerprint recognition is widely used for verification and identificati...

Feature Level Fusion of Biometrics Cues: Human Identification with Doddingtons Caricature

This paper presents a multimodal biometric system of fingerprint and ear...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.