HomePage
FPGA implementation of decision functions
Generalized Fourier Descriptors
Curvilinear detector
Viola Jones hardware implementation
Cancer Prostate
Contact
Demo
Hobbies

Fethi Smach, PhD student, is working on the application of Generalized Fourier Descriptors combined with SVM, for color object recognition. He studied the classification performance and the hardware implementation of these descriptors. The work is performed in collaboration with Sfax University - Tunisia, with Mohamed Abid.

Abstract

Fourier Descriptors can be used as feature vector components in various applications, such as real-time color object recognition or image retrieval. The full process is composed of the feature extraction followed by a classification step performed using Support Vector Machine (SVM). In order to accelerate the computation of Fourier Descriptors, a hardware implementation using FPGA technology is presented in this paper. We evaluated classification performance with respect to lighting variations and noise sensibility. Several experiments were carried out on three databases. Then an efficient architecture for FD computation on FPGAs is proposed and designed as accelerator. The WildCard is used to prototype this implementation. This design can have an operation speed up of approximately 10 compared to the standard software PC implementation.

 

 

Publications about Generalised Fourier Descriptors:

  • Journals

    • "Generalized Fourier Descriptors with Applications to Objects Recognition in SVM Context", Fethi SMACH, Cédric LEMAITRE, Jean Paul GAUTHIER, Johel MITERAN, Mohamed ATRI, Journal of Mathematical Imaging and Vision (JMIV), Springer, 2007, JMIV.pdf
    • "An FPGA-based accelerator for Fourier Descriptors computing for color object recognition using SVM", Fethi SMACH, Johel MITERAN, Mohamed ATRI, Julien DUBOIS, Mohamed ABID, Jean Paul GAUTHIER, Journal of Real-Time Image Processing (JRTIP), Springer, 2007, JRTIPversion_18draft.pdf
    • "Design of a Neural Networks Classifier for Face Detection", Fethi SMACH, Mohamed ATRI, Johel MITERAN, Mohamed ABID, Journal of Computer Science, Sciences Publications, 2 (3), pp. 261-268, 2006, http://www.scientificworld.net/fulltext/jcs/jcs23257-260.pdf

    International conferences

    • "A comparative study of motion descriptors and Zernike moments in color object recognition", Cédric LEMAITRE, Fethi SMACH, Johel MITERAN, Jean Paul GAUTHIER, Mohamed ATRI, to appear in the proceeding of International Multi-Conference on Systems, Signal and Devices (SSD), IEEE, Hammamet, Tunisia, 2007, SSDEnCours.pdf
    • "Finding Invariants of Group Actions on Function Spaces, a General Methodology From non-Abelian Harmonic Analysis", Jean Paul GAUTHIER, Fethi SMACH, Cédric LEMAITRE, Johel MITERAN, Workshop on Mathematical Control Theory, Lisbon, Portugal, 2007, pdfesc.pdf
    • "Colour Object recognition combining Motion Descriptors, Zernike Moments and Support Vector Machine", Fethi SMACH, Cédric LEMAITRE, Johel MITERAN, Jean Paul GAUTHIER, Mohamed ATRI, Proceedings of IECON'06, IEEE, Paris-CNAM, France, pp. 3238-3242, 2006, papier_IECON.pdf
    • "Design of a Neural Networks Classifier for Face Detection", Fethi SMACH, Mohamed ATRI, Johel MITERAN, Mohamed ABID, ENOFORMATIKA 5, pp. 274-277, 2005.

    French conferences 

    • "Reconnaissance d'objets 3D couleur à l'aide des descripteurs de Fourier Généralisés et des SVM", Fethi SMACH, Cédric LEMAITRE, Johel MITERAN, Jean Paul GAUTHIER, Journées d'étude SEE/GRD ISIS : La reconnaissance des formes : quelles méthodes pour quelles applications?, 2006, Resume_gdr_RBF06.pdf
Generalized Fourier Descriptors