SIFT and SURF Descriptors for Face Recognition using Wavelet Transform

Automatic face recognition is a major research area in computer vision which aims to recognize human face without human intervention. Significant developments in this field have shown that in many face recognition applications the automated techniques outperform human. The key problem in face recognition is how to find a feature set to identify a face. Many algorithms about feature extraction have been proposed, which mainly include three aspects: face geometrical, facial and statistical features. In this book, the conventional SIFT and SURF performances are tested in face recognition. They provide high performance. However, this performance can be improved further by transforming the input into different domain from the real time. Hence, we apply Discrete Wavelet Transform (DWT) or Gabor Wavelet Transform (GWT) at the input face images which provides us denser and clearer images compared to those by the conventional SIFT or SURF. Simulations show that the proposed approaches based on DWT or GWT using SIFT or SURF provides very high performance compared to the conventional algorithms.

Autorentext

Musa M.Ameen received the B.Sc. degree in Computer Engineering from Ishik University, Iraq in 2013, and M.Sc. degree in Computer Engineering from Mevlana University, Turkey in 2016. Currently, he works as Lecturer at Ishik University, Iraq. His current research interests are biometrics, computer vision, and signal processing.