Evaluation of realistic blurring image quality by using a shallow convolutional neural network

Manifold causes of image blurring make the no-reference evaluation of realistic blurred images very challenging. Previous studies indicate that handcrafted features suffer from poor representation of the intrinsic characteristics of image blurring and thus blind image sharpness assessment (BISA) is unsatisfactory. This paper explores a shallow convolutional neural network (CNN) to address this problem facilitated by data augmentation. Superior to algorithms that necessitates considerable expertise and efforts to handcraft features for optimal representation of perceptual image quality, CNN directly integrates the retrieval of intrinsic features and the prediction of image blur quality into an optimization process. Moreover, experiments on Realistic Blurring Image Database have verified that CNN advances in retrieving intrinsic features and obtains good correlation with subjective image blurring evaluations.