Face tracking by 3-D dual-tree complex wavelet transform using support vector machine
Azadeh Mansouri, Farah Torkamani Azar, Ahmad Mahmoudi-Aznaveh · 2007
The main objective of this research is the design of a new method for tracking special moving objects(faces), using Complex Wavelet Transform (CopfWT) and Support Vector Machine (SVM) classifier as a suitable binary classification system. By using motion-selective properties of 3-D-CopfWT , moving objects can be separated from background in 3-D signals like video. The selected objects applied to the SVM classifier and the positive answers of the system were interpreted as special objects.