arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.02554cs.CV
收藏

一种有效的对比度失真图像无参考质量评价与分类模型

Efficient No-Reference Quality Assessment and Classification Model for Contrast Distorted Images

École de technologie supérieure(高等技术学院);Synchromedia Laboratory for Multimedia Communication in Telepresence(远程呈现多媒体通信同步媒体实验室)

Hossein Ziaei Nafchi, Mohamed Cheriet

摘要:

提出了一种基于Minkowski距离的无参考图像质量评价方法。结果表明,高阶的Minkowski距离和熵提供准确的质量预测的对比度失真的图像。所提出的度量进行预测,只提取三个功能,然后从失真的图像进行回归分析。此外,所提出的功能是能够分类类型的对比度失真的图像具有较高的精度。在CSIQ、TID 2013、CCID 2014和SIQAD四个数据集上的实验结果表明,该度量具有非常低的复杂度,比最先进的NR度量提供了更好的预测质量。建议度量的MATLAB源代码可在http://www.synchromedia.ca/system/files/MDM.zip上向公众提供。

英文摘要:

In this paper, an efficient Minkowski Distance based Metric (MDM) for no-reference (NR) quality assessment of contrast distorted images is proposed. It is shown that higher orders of Minkowski distance and entropy provide accurate quality prediction for the contrast distorted images. The proposed metric performs predictions by extracting only three features from the distorted images followed by a regression analysis. Furthermore, the proposed features are able to classify type of the contrast distorted images with a high accuracy. Experimental results on four datasets CSIQ, TID2013, CCID2014, and SIQAD show that the proposed metric with a very low complexity provides better quality predictions than the state-of-the-art NR metrics. The MATLAB source code of the proposed metric is available to public at http://www.synchromedia.ca/system/files/MDM.zip.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑