Image Reconstruction Using Zernike Moment and Discrete Cosine Transform: A Comparison

Image reconstruction is very much concerned with the ability to reproduce image of possibly the same quality as original. This paper presents the comparison of Zernike Moment (ZM) and Discrete Cosine Transform (DCT) for image reconstruction in noise environment. Two types of images used are gray scale and binary. The original images are corrupted with three different noises that are Salt and Pepper, Gaussian and Random. Both original and corrupted images are reconstructed using Inverse Zernike Moment and Inverse Discrete Cosine Transform. The performance of each algorithm is measured by evaluating Peak Signal to Noise Ratio (PSNR) for the reconstructed gray scale of pixel size 64×64 and binary of pixel size 30×30 images. The comparison of PSNR values between the two techniques proves that Zernike Moment is less sensitive to noisy images compared to Discrete Cosine Transform.

I. Introduction

Image reconstruction basically is useful in many areas for instance reconstruction of medical images, in biometrics such as fingerprint reconstruction for security purposes, face and gait recognition and many more. The goal of image reconstruction is to retrieve image information that has been lost in the image formation. In contrast to image enhancement, image reconstruction is an objective approach to recover a degraded image based on mathematical and statistical models.