Visual Importance Pooling for Image Quality Assessment
Visual Importance Pooling for Image Quality Assessment
复制标题
DOI：
10.1109/jstsp.2009.2015374
复制
发表时间：
2009-04-01
影响因子：
7.5
通讯作者：
Bovik, Alan Conrad
中科院分区：
文献类型：
--
作者：
Moorthy, Anush Krishna;Bovik, Alan Conrad
最近的图像质量评估（IQA）指标与人类对图像质量的感知具有高度相关性。当然，产生更好的结果是有兴趣的。一种有前途的方法是通过视觉重要性来衡量图像质量测量。为此，我们描述了两种策略——基于视觉固定的加权和基于质量的加权。通过与之前的一些研究对比，我们发现这些策略可以显着提高与主观判断的相关性。我们使用 LIVE 数据库作为测试平台，展示了 SSIM 索引在多尺度和单尺度版本中的改进。
Recent image quality assessment (IQA) metrics achieve high correlation with human perception of image quality. Naturally, it is of interest to produce even better results. One promising method is to weight image quality measurements by visual importance. To this end, we describe two strategies-visual fixation-based weighting, and quality-based weighting. By contrast with some prior studies we find that these strategies can improve the correlations with subjective judgment significantly. We demonstrate improvements on the SSIM index in both its multiscale and single-scale versions, using the LIVE database as a test-bed.