IEEE Trans Cybern. 2018 Apr;48(4):1276-1289. doi: 10.1109/TCYB.2017.2690452. Epub 2017 Apr 13.
The goal of image retargeting is to adapt source images to target displays with different sizes and aspect ratios. Different retargeting operators create different retargeted images, and a key problem is to evaluate the performance of each retargeting operator. Subjective evaluation is most reliable, but it is cumbersome and labor-consuming, and more importantly, it is hard to be embedded into online optimization systems. This paper focuses on exploring the effectiveness of sparse representation for objective image retargeting quality assessment. The principle idea is to extract distortion sensitive features from one image (e.g., retargeted image) and further investigate how many of these features are preserved or changed in another one (e.g., source image) to measure the perceptual similarity between them. To create a compact and robust feature representation, we learn two overcomplete dictionaries to represent the distortion sensitive features of an image. Features including local geometric structure and global context information are both addressed in the proposed framework. The intrinsic discriminative power of sparse representation is then exploited to measure the similarity between the source and retargeted images. Finally, individual quality scores are fused into an overall quality by a typical regression method. Experimental results on several databases have demonstrated the superiority of the proposed method.
图像重定目标的目的是将源图像适配到具有不同大小和纵横比的目标显示器上。不同的重定目标操作符会创建不同的重定目标图像，一个关键问题是评估每个重定目标操作符的性能。主观评估是最可靠的，但它很繁琐且耗费精力，更重要的是，它很难嵌入到在线优化系统中。本文专注于探索稀疏表示在客观图像重定目标质量评估中的有效性。其基本思想是从一幅图像（例如，重定目标图像）中提取失真敏感特征，并进一步研究这些特征中有多少在另一幅图像（例如，源图像）中被保留或改变，以测量它们之间的感知相似性。为了创建紧凑而稳健的特征表示，我们学习了两个过完备字典来表示图像的失真敏感特征。所提出的框架中同时考虑了局部几何结构和全局上下文信息等特征。然后，利用稀疏表示的内在判别能力来测量源图像和重定目标图像之间的相似性。最后，通过典型的回归方法将各个质量分数融合为整体质量。在几个数据库上的实验结果表明了该方法的优越性。
