Image sharpening using dilated filters

Abstract

Digital photography is growing in the mobile device industry. Due to considerable variety of sensors used for images capture and hardware limitations the quality of obtained images is not always the desired one. A large amount of research has been done in the field of image de-noising and sharpening in order to compensate this effect. Encouraged by the positive results obtained by using dilated filters in edge detection domain we explore the usage of this concept in classical sharpening algorithms. In this paper we propose an enhancement of classical low-cost computational solutions for sharpening like High Pass Filter (HPF) and Unshap Masking (UM) by using dilated filters concept. The proposed modified sharpening algorithms obtain better results visually and statistically than the classical approaches.