Title: Multiobjective genetic algorithm-based adaptive wavelet design

Authors: Sameh Fakhfakh Ghribi; Ameni Yangui Jammoussi; Dorra Sellami Masmoudi

Addresses: CEMlab Research Laboratory, University of Sfax, National School of Engineers (ENIS), POB W, 3038 Sfax, Tunisia ' CEMlab Research Laboratory, University of Sfax, National School of Engineers (ENIS), POB W, 3038 Sfax, Tunisia ' CEMlab Research Laboratory, University of Sfax, National School of Engineers (ENIS), POB W, 3038 Sfax, Tunisia

Abstract: Wavelet performances differ from one application to another and from one database to another. In this case, one can try to find out for each application the appropriate wavelet transform which results in better performances and consumes minimal resources once implemented on an FPGA platform. Accordingly, we use a generic lifting wavelet transform with p₀ and q parameters. Thus, we train the optimisation process with a multi-objective genetic algorithm for optimising wavelet transform with respect to specific applications. Optimised criteria are related to wavelet regularity and the undertaken application performances. We consider pattern recognition and image compression applications processed respectively on ORL database and a fingerprint database. Compared with DB 4 and DB 9/7, the improvement of the criterion related to the application reaches 17% for pattern recognition application and preserves, approximately, the same values for still image compression in addition to the minimisation of the hardware cost.

Keywords: wavelet transform; lifting implementation; image coding; pattern recognition; non-dominated sorting genetic algorithms; NSGA-II; FPGA; field-programmable gate arrays; adaptive wavelet design; multi-objective optimisation; image compression.

DOI: 10.1504/IJCVR.2016.073763

International Journal of Computational Vision and Robotics, 2016 Vol.6 No.1/2, pp.127 - 145

Received: 07 Jan 2014
Accepted: 21 Sep 2014
Published online: 18 Dec 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article