Binary image quality assessment—a hybrid approach based on binarization evaluation methods

Abstract

In the paper the idea of multiple metrics fusion for binary image quality assessment is presented together with experimental results obtained using the images from Bilevel Image Similarity Ground Truth Archive. As the performance evaluation of any full-reference image quality assessment metric requires both the knowledge of reference images with perfect quality and the results of subjective evaluation of distorted images, several such datasets have been developed during recent years. Nevertheless, the specificity of binary images requires the use of some other metrics which should also be verified in view of their correlation with subjective perception. Such task can be done using a dedicated database of binary images followed by the combination of multiple metrics leading to even higher correlation with subjective scores presented in this paper.