Distortion-specific feature selection algorithm for universal blind image quality assessment

Abstract

Blind image quality assessment (BIQA) aims to use objective measures for predicting the quality score of distorted images without any prior information regarding the reference image. Several BIQA techniques are proposed in literature that use a two-step approach, i.e., feature extraction for distortion classification and regression for predicting the quality score. In this paper, a three-step approach is proposed that aims to improve the performance of BIQA techniques. In the first step, feature extraction is performed using existing BIQA techniques to determine the distortion type. Secondly, features are selected for each distortion type based on the mean value of Spearman rank ordered correlation constant (SROCC) and linear correlation constant (LCC). Lastly, distortion-specific features are used by regression model to predict the quality score. Experimental results show that the predicted quality score using distortion-specific features strongly correlates with the subjective quality score, improves the overall performance of existing BIQA techniques, and reduces the processing time.

Blind Image Quality Assessment for Super Resolution via Optimal Feature Selection

“…Other works have also explored feature selection for BIQA [51], [52]. They analyzed each feature individually by training a model and determining its performance with different metrics such as Spearman rank correlation coefficient (SRCC), PCC, root mean square error and Kendall correlation coefficient.…”

Quality Assessment of Stereoscopic 360-degree Images from Multi-viewports

“…Compared with conventional 2D image quality assessment (IQA), it is more challenging to evaluate the quality of stereoscopic panoramic images due to the unlimited field of view (FoV) and extra dimension of depth perception [4]. Although IQA has been researched in recent years [5]- [7], a few works have been done to predict the perceptual quality of stereo 360 images which remains an intractable research problem.…”