FINGERPRINT COMPRESSION BASED ON SPARSE REPRESENTATION?
Journal: International Journal of Computer Science and Mobile Computing - IJCSMC (Vol.4, No. 3)Publication Date: 2015-03-30
Authors : Linda J Goldina; Y. Baby Kalpana;
Page : 172-179
Keywords : patches; sparse;
Abstract
A new fingerprint compression algorithm based on sparse representation is introduced. Obtaining an over complete dictionary from a set of fingerprint patches allows us to represent them as a sparse linear combination of dictionary atoms. We first construct a dictionary for predefined fingerprint image patches. For a new given fingerprint images, represent its patches according to the dictionary by computing l0-minimization and then quantize and encode the representation. In this paper, we consider the effect of various factors on compression results. Three groups of fingerprint images are tested. The experiments demonstrate that our algorithm is efficient compared with several competing compression techniques (JPEG, JPEG 2000, and WSQ), especially at high compression ratios. The experiments also illustrate that the proposed algorithm is robust to extract minutiae.
Other Latest Articles
- Evaluation of Stemming Techniques for Text Classification?
- Mobile Based Campus Information Retrieval Android Application?
- COMPARATIVE STUDY: WATERFALL V/S AGILE MODEL
- STUDY OF JUTE/GLASS EPOXY BASED HYBRID COMPOSITES
- APPLICATION OF LOGISTIC MODEL FOR STUDYING THE FACTORS AFFECT ACADEMIC ACHIEVEMENT OF THE STUDENT - CASE STUDY OF FACULTY OF SCIENCES AND HUMANITIES (THADIQ) -SHAQRAA UNIVERSITY-KSA
Last modified: 2015-03-20 01:18:56