No-reference quality metric for watermarked images based on combining of objective metrics using neural network

In this paper, a new no-reference image quality metric is proposed to estimate the quality of watermarked images automatically based on combining objective metrics using neural network. The aim is to predict the subjective quality scores, known as the mean opinion score (MOS) obtained from human observers. In practice, our metric consists of three stages: first, filtering process is applied to watermarked image in order to generate its filtered image. Second, we use watermarked image and its filtered image in the calculation of the objective metrics as input to a neural network. Third; these metrics are combined using neural network model. The output of this neural network is a single value corresponding to the MOS scores. Experimental results show that combination of objective metrics through the neural network, indeed is able to accurately predict perceived quality of watermarked images.