Learning to Rank for Blind Image Quality Assessment
Learning to Rank for Blind Image Quality Assessment
复制标题
DOI：
10.1145/3424978.3425111
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Lihao Zheng;Genyuan Zhang;Yaping Cai
中科院分区：
文献类型：
--
作者：
Lihao Zheng;Genyuan Zhang;Yaping Cai
针对现有盲图像质量评价模型的不足，提出了一种基于学习排序方法的盲图像质量评价模型。在该模型中，我们首先通过对图像质量偏好的分类来简化预测图像质量分数的问题，然后使用特征融合和基于组Lasso的多核学习(MKLGL)方法来训练分类器。最后，基于投票策略，构建了一个简单有效的图像质量预测模型。在现有IQA数据集上的实验结果表明，该方法与人眼的主观感知高度一致，优于现有的BIQA方法。此外，我们的方法具有高度的可扩展性。
We propose a blind image quality assessment (BIQA) model using learning to rank (LTR) method in order to overcome the defects of the existing BIQA model. In this model, we first simplify the problem of predicting exact image quality score with the classification of image quality preference and we then use feature fusion and multiple kernel learning based on group lasso (MKLGL) methods to train a classifier. Finally, based on the voting strategy, a simple and effective image quality prediction model is constructed. Experimental results on the existing IQA datasets show that our proposed method is highly consistent with the subjective perception of human eyes and is superior to existing BIQA methods. In addition, our method is highly scalable.