Defocus blur-invariant scale-space feature extractions

Date of Award


Degree Name

Ph.D. in Electrical Engineering


Department of Electrical and Computer Engineering


Advisor: Keigo Hirakawa


We propose modifications to scale-space feature extraction techniques (Scale-Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF)) that make the feature detection and description invariant to defocus blur. Specifically, scale-space blob detection relies on the second derivative responses of images. Our analysis of defocus blur and its effect on scale-space blob detection suggests that fourth derivative and not the usual second derivative is optimal for detecting the blurred blobs while multi-scale descriptors of blurred blobs are effective at establishing correspondences between blurred images. The proposed defocus blur-invariant (DBI) scale-space feature extraction techniques which we refer to as DBI-SIFT and DBI-SURF do not require image deblurring nor blur kernel estimation, meaning that their accuracy does not depend on the quality of image deblurring. We offer empirical evidence of blur invariance by establishing interest point correspondences between sharp or blurred reference images and blurred target images.


Image analysis, Image processing Digital techniques, Optical pattern recognition, Electrical Engineering, SIFT, SURF, DBI-SIFT, DBI-SURF

Rights Statement

Copyright 2014, author