Learning to Rank for Blind Image Quality Assessment

• Published in: IEEE transaction on neural networks and learning systems Vol. 26; no. 10; pp. 2275 - 2290
• Main Authors: Gao, Fei, Tao, Dacheng, Gao, Xinbo, Li, Xuelong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Assessments; Blinds; Customer satisfaction; Feature extraction; Image coding; Image quality; Image quality assessment (IQA); Learning; learning preferences; learning to rank; Mathematical models; multiple kernel learning (MKL); Noise; Observers; Quality of service; Training; Transform coding; universal blind IQA (BIQA); Image quality assessment (IQA); learning preferences; universal blind IQA (BIQA); learning to rank; multiple kernel learning (MKL)

Blind image quality assessment (BIQA) aims to predict perceptual image quality scores without access to reference images. State-of-the-art BIQA methods typically require subjects to score a large number of images to train a robust model. However, subjective quality scores are imprecise, biased, and...