Date of Award:

6-5-2015

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Computer Science

Advisor/Chair:

Vladimir Kulyukin

Abstract

Efficient detection of image blur and its extent is an open research problem in computer vision. Image blur has a negative impact on image quality. Blur is introduced into images due to various factors including limited contrast, improper exposure time or unstable device handling. Toward this end, an algorithm is presented for image blur detection with the use of Two-Dimensional Haar Wavelet transform (2D HWT). The algorithm is experimentally compared with two other image blur detection algorithms frequently cited in the literature. When evaluated over a sample of images, the algorithm performed on par or better than the two other blur detection algorithms.

Share

COinS