6533b827fe1ef96bd1286dc0

RESEARCH PRODUCT

Multiscale Edges Detection by Wavelet Transform for Model of Face Recognition

Michel PaindavoineMichel PaindavoineHervé AbdiHervé AbdiFan YangFan Yang

subject

Discrete wavelet transformLifting schemePixelComputer sciencebusiness.industrySecond-generation wavelet transformComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONWavelet transformPattern recognitionImage processingFacial recognition systemWaveletComputer visionArtificial intelligencebusiness

description

Publisher Summary The linear auto-associator is a particular case of the linear-associator. The goal of this network is to associate a set of stimuli to itself, which could be used to store and retrieve face images and it also could be applied as a pre-processing device to simulate some psychological tasks—such as categorizing face according to their gender. A technique of learning based on the wavelet transform can improve recognition capability when the pattern images are with a great noise. One of the ways to store and recall face images uses the linear auto-associative memory. This connectionist model is in conjunction with a pixel-based coding of the faces. The image processing using the wavelet transform can be applied to the multiscale edges detection. This chapter describes a technique of learning for the auto-associator based on wavelet transform and a 17% improvement of the performances for face recognition has been obtained in comparison with the standard learning.

yearjournalcountryeditionlanguage
1996-01-01
https://doi.org/10.1016/b978-044482587-2/50091-4