作者: Lihuo He , Dongxue Wang , Xuelong Li , Dacheng Tao , Xinbo Gao
DOI: 10.1007/978-3-642-34481-7_49
关键词: Mathematics 、 Color quantization 、 Color normalization 、 HSL and HSV 、 Artificial intelligence 、 Color balance 、 Distortion 、 Image quality 、 Support vector machine 、 Color histogram 、 Computer vision
摘要: Developing reduced reference image quality assessment (RR-IQA) plays a vital role in dealing with the prediction of visual distorted images. However, most existing methods fail to take color information into consideration, although distortion is significant for increasing To solve aforementioned problem, this paper proposed novel IQA method which focuses on distortion. In particular, we extract features based model fractal structure. Then and structure are mapped using support vector regression. Experimental results LIVE II database demonstrate that has good consistency human perception especially images