Image quality assessment using Elman neural network model

Abstract

Measurement of visual quality is of fundamental importance for numerous image and video processing applications, where the goal of quality assessment algorithms is to automatically assess the quality of images or videos in agreement with human quality judgments. This research aims to develop a no reference image quality measurement algorithms for JPEG images. A JPEG image database was created and subjective experiments were conducted on the database. An attempt to design a computationally inexpensive and memory efficient feature extraction method has been developed. Subjective test results are used to train the neural network model, which achieves good quality prediction performance without any reference image. The system has been implemented and tested for its validity. Experimental results show that the image quality was recognized correctly at a rate of 89.23%.