No-reference image quality assessment is of great importance to numerous image processing applications, and various methods have been widely studied with promis-ing results. These methods exploit handcrafted features in the transformation or space domain that are discriminated for image degradations. However, abundant a priori knowl-edge is required to extract these handcrafted features. The convolutional neural network (CNN) is recently introduced into the no-reference image quality assessment, which inte-grates feature learning and regression into one optimization process. Therefore, the network structure generates an effec-tive model for estimating image quality. However, the image quality score obtained by the CNN is based on the mean of all of the image patch scores without considering the human visual system, such as edges and contour of images. In this paper, we combine the CNN and the Prewitt magnitude of segmented images and obtain the image quality score using the mean of all the products of the image patch scores and weights based on the result of segmented images. Experi-mental results on various image distortion types demonstrate that the proposed algorithm achieves good performance.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below