Learning to predict the perceived visual quality of photos

Abstract

Visual quality (VisQ) representation is a fundamental step in the learning of a VisQ prediction model for photos. It not only reflects how we understand VisQ but also determines the label type. Existing studies apply a scalar value (i.e., a categorical label or a score) to represent VisQ. As VisQ is a subjective property, only a scalar value is insufficient to represent human's perceived VisQ of a photo. This study represents VisQ by a distribution on pre-defined ordinal basic ratings in order to capture the subjectivity of VisQ better. When using the new representation, the label type is structural instead of scalar. Conventional learning algorithms cannot be directly applied in model learning. Meanwhile, for many photos, the numbers of users involved in the evaluation are limited, making some labels unreliable. In this study, a new algorithm called support vector distribution regression (SVDR) is presented to deal with the structural output learning. Two independent learning strategies (reliability-sensitive learning and label refinement) are proposed to alleviate the difficulty of insufficient involved users for rating. Combining SVDR with the two learning strategies, two separate structural-output regression algorithms (i.e., reliability-sensitive SVDR and label refinement-based SVDR) are produced. Experimental results demonstrate the effectiveness of our introduced learning strategies and learning algorithms.