Abstract: An important place in the problems of digital image analysis is occupied by the task of enlarging the resolution of an image by scaling it. Such tasks include, in particular: obtaining more detailed information from a fragment of an image because of its enlargement; image magnification for object identification; obtaining a high-resolution image from a low-resolution image to facilitate its further detailed analysis, etc. Each of the existing technics is characterized by both the positive and negative sides. In particular, the negative side is the distortion of the geometric shape of small parts and damage to the texture of the image. Interpolation algorithms are used to reduce these disadvantages. One approach to solve this problem is to use interpolation techniques. The presented article attempts to use the generalized interpolation formulae (Piranashvili’s formulae) with a high-speed convergence for the task of enlarging image size. The results of using Whittaker-Kotelnikov-Shannon and Piranashvili interpolation formulae for enlarging digital images are shown. To estimate the accuracy and quality of approximation of images obtained after interpolation, the remainder terms and signal-to-noise ratio (SNR) values are calculated and compared.
Keywords: Image interpolation, Digital image enlarging, Whittaker-Kotelnikov-Shannon interpolation, Generalized interpolation formulae, Remainder term, Signal-to-noise ratio.
|
DOI:
10.17148/IJARCCE.2024.13624
