Local Feature Descriptor and Derivative Filters for Blind Image Quality Assessment

Abstract

In this letter, a novel blind image quality assessment (BIQA) technique is introduced to provide an automatic and reproducible evaluation of distorted images. In the approach, the information carried by image derivatives of different orders is captured by local features and used for the image quality prediction. Since a typical local feature descriptor is designed to ensure a robust image patch representation, in this letter, a novel descriptor that additionally highlights local differences enhanced by the filtering is proposed. Furthermore, a set of derivative kernels is introduced. Finally, the support vector regression technique is used to map statistics of described local features into subjective scores, providing an objective quality score for an image. Extensive experimental validation on popular IQA image datasets reveals that the proposed method outperforms the state-of-the-art handcrafted and deep learning BIQA measures.