PGF-BIQA: Blind image quality assessment via probability multi-grained cascade forest

Abstract

Blind image quality assessment (BIQA) aims to automatically predict the perceptual quality of a digital image without accessing its pristine reference and plays an important role in computer vision and image analysis. In fact, the difference in the subjective perception of image quality by evaluators greatly affected quality scores of the images. Aiming at the problem that the existing models cannot take into account the subjective perception differences in people, a blind image quality assessment algorithm via probability gcForest (PGF-BIQA) is proposed. Specifically, we use five qualitative labels to replace the specific quality score and extract image color and texture features to represent image quality. Unlike the widely used neural network, gcForest is ensemble by decision trees which randomly extract different features of various modes to learn the relationship between label and quality features. Therefore, a probability gcForest is designed, combining the frequency probability model and the gcForest, using probability confidence to represent the multiple decision modes results, and describing the subjective perception differences in evaluators. Next, through quality anchors and probability confidences of different classes, PGF-BIQA achieves image quality assessment. Moreover, this method proposes an image classification method that resolves the problem of an unbalanced number of images of different classes and the calculation process of the algorithm is simple and effective. Extensive experiments demonstrate that the proposed method is highly consistent with human perception and outperforms many state-of-the-art BIQA algorithms.