Grey wolf optimizer based IQA of mixed and multiple distorted images

Due to quality degradations induced at various phases of visual signal capture, compression, transmission, and display, perceptual quality evaluation is crucial in visual communication systems. This work addresses the issue of evaluating the quality of photographs that contain multiple distortions. We propose a modified Grey Wolf Optimizer (MGWO) image quality assessment (IQA) algorithm and compare its performance with conventional IQA and Feed Forward Back Propagation-Neural Network (FFBP-NN). Signal-to-noise ratio (SNR), peak signal-to-power ratio (PSNR), mean-square error (MSE), root mean-square error (RMSE), and piecewise flat embedding (PFE) are considered as the performance evaluation metrics. The results show that the proposed MGWO-IQA can achieve substantially greater consistency with subjective assessments as compared to the state-of-the-art IQA measures, according to extensive trials conducted. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.