Multimodal Expression-Invariant Face Recognition Using Dual-Tree Complex Wavelet Transform

A new multimodal face recognition method whichextracts features of rigid and semi-rigid regions of the face usingDual-Tree Complex Wavelet Transform (DT-CWT) is proposed.DT-CWT decomposes range and intensity images into eight subimagesconsisting of six band-pass sub-images to represent facedetails and two low-pass sub-images to represent faceapproximates. In this work, support vector machine (SVM) hasbeen used as the classifier. The proposed method has beenevaluated using the face BU-3DFE dataset containing a widerange of expression changes. Findings include the overallidentification rate of 98.1% and the overall verification rate of99.3% at 0.1% false acceptance rate

Keywords:

face recognition , multimodal , complex wavelet expression invariant , SVM