A REVIEW REPORT ON FINGERPRINT IMAGE ENHANCEMENT FILTER
DINESH KUMAR MISRA
1
, S. P. TRIPATHI
2
& DIPAK MISRA
3
1
Ph.D, Research Scholar, COE, TMU, Moradabad, Uttar Pradesh, India
2
Professor & Head, CSE Department, GBTU, Lucknow, Uttar Pradesh, India
3
Scholar, EC Department, VIT University, Vellore, Tamil Nadu, India
ABSTRACT
This research aims to study diffrent kind of filter applied for fingerprint image enhancement. The fingerprint
images which are obtained from sensors, scanning or imaging devices may be dirty, ink blurred or infected during
acquisition process. The quality of a fingerprint image directly affects the performance of feature extraction and
recognition system, so it is necessary to enhance fingerprint image by some method. Enhancement techniques are so
varied, and use so many different image processing approaches, that it is difficult to assemble a meaningful body of
techniques suitable for enhancement without extensive background development. For this reason an attempt is made to
bring review on fingerprint enhancement filters and algorithms in this paper.
KEYWORDS: Fingerprint Image, Imaging Device, Gray-Scale Image, Ridge and Valley, Filters, Image Processing,
Fuzzy Filter, Enhancement Algorithm
INTRODUCTION
Fingerprint images are acquired by pressing or rolling a finger against a hard surface (e.g. glass, silicon, and
polymer) or paper (e.g. index card). The image acquisition process introduces non-linear distortions in the ridge structure
and consequently in the spatial location of minutiae points.
This distortion is a function of several parameters including the orientation of the sensor with respect to the finger,
the amount of pressure applied by the subject, the disposition of the subject (sitting or standing), the motion of the finger
prior to its placement on the sensor, the moisture content of the skin (dry, oily or wet), the elasticity of the skin etc. [2] The
distortion can result in significant number of spurious minutiae being created and genuine minutiae being ignored.
The fingerprint image enhancement is a preprocessing technique to make the image clearer than the original
image, for further operations as shown in Figure1.However in practice, due to variation in impressions conditions, ridge
configuration, skin condition (aberrant formations of epidermal ridges of fingerprints, postnatal marks and occupational
marks), acquisition devices and non co-operative attitude of subjects etc, a significant percentage of acquired fingerprint
images, approximately 10% are of poor quality.
This „poor‟ quality image is marked by low contrast, ill-defined and indistinct boundaries between the ridges and
valleys.[4] The poor quality image such as: arid, wet or damp, smudge, scars,blurred and wrinkle degrades effectiveness of
the algorithm.
Thus image required to be enhanced at significant level to proceed furthure matching or recognition process. Main
reason for performing enhancement is to eradicate the noise in the fingerprint images, improve the quality of image,
illuminate the parallel ridges and valleys and reconstruct actual image to the possible instant of true image.
International Journal of Computer Science Engineering
and Information Technology Research (IJCSEITR)
ISSN 2249-6831
Vol. 3, Issue 2, Jun 2013, 403-416
© TJPRC Pvt. Ltd.