Title :
A Novel Quality Metric for Image Fusion Based on Color and Structural Similarity
Author_Institution :
Inst. of Image & Graph, Sichuan Univ., Chengdu, China
Abstract :
A new objective quality metric without reference for color fused image is proposed in this paper. This measurement combines the color similarity with the structural similarity between the source images and the fused image. The color similarity is directly computed in RGB color space and is compose of the hue and saturation similarity and intensity similarity. The value of image quality is obtained by weighted average of the color similar coefficients between the source images and the fused image. The weighing factor is decided by the structural similarity index between the source images and the fused image. Compared to other measures, this quality metric is easier to compute. Experiments show that the metric is consistent with the subjective evaluations and outperforms other objective evaluation metrics.
Keywords :
image colour analysis; image fusion; RGB color space; color fused image; color similar coefficients; color similarity; hue similarity; image fusion; image quality; intensity similarity; quality metric; saturation similarity; source images; structural similarity; Computer science; Educational institutions; Gray-scale; High-resolution imaging; Humans; Image color analysis; Image fusion; Image quality; Image resolution; Signal processing; color similarity; image fusion; image quality metric; structural similarity index;
Conference_Titel :
2009 International Conference on Signal Processing Systems
Conference_Location :
Singapore
Print_ISBN :
978-0-7695-3654-5
DOI :
10.1109/ICSPS.2009.72