Enlargement of Image Based Upon Interpolation Techniques

Abstract: For real time applications, simple linear or cubic interpolation and FCBI (Fast Curvature Based Interpolation) algorithms are applied for the task of enlargement of images without changing super resolution (low resolution and high resolution), but the results obtained are not really satisfactory, being affected by relevant artifacts like blurring and jaggies. In this paper we describe a new method (ICBI, Iterative Curvature Based Interpolation) based on a two-step grid filling and an iterative correction of the interpolated pixels obtained by minimizing an objective function depending on the second order directional derivatives of the image intensity. We need to compare ICBI with FCBI in two cases that is PSNR (Peak Signal to Noise Ratio) test and time calculations for ICBI and FCBI.
We show that the constraints used to derive the function are related with those applied in another well-known interpolation method providing good results. The high quality of the images enlarged with the new method is demonstrated with objective and subjective tests, and PSNR for ICBI is 30.085 dB (ZF=002), 23.833dB (ZF=004).

Keywords: Fast Curvature Based Interpolation, Iterative Curvature Based Interpolation, Fast Methods And The NEDI Algorithm, Perceptually-Inspired An Edge-Directed Color, Image Super- Resolution, New Edge –Directed Interpolation