Reduced-reference image quality assessment method based on wavelet feature extraction and fusion

Abstract

Virtual reality has many characteristics such as multi-sensation, interactivity, and presence. Virtual reality images, also known as 360-degree panoramic images, provide users with an immersive experience and have been widely used in education, medical, military and many other fields in recent years. 360-degree panoramic images have high resolution and are subject to varying degrees of distortion during transmission and storage. Therefore, the evaluation of virtual reality images has practical significance. To this end, we propose a method for evaluating the quality of images in the new CVIQD database. The proposed image quality assessment model is developed based on Haar wavelet and Db4 wavelet feature extraction and fusion. The method is compared with a single wavelet feature extraction method. Experiments show that the method has better performance.