融合显著物体检测的图像显示适配

Image retargeting based on salient object detection

目的图像显著适配旨在自动调节图像尺寸,对图像内容进行非均匀缩放,以便在受限的展示空间内更好地保留显著物体。为了解决显示适配过程中显著物体部分扭曲的问题,提出一种基于显著物体检测的图像显示适配方法。方法本文方法采用显著物体分割结果来替代显著性图,以改进显示适配结果。首先,采用显著性融合和传播的方法生成显著性图;接着,结合输入图像和显著性图,采用自适应三阈值方法实现显著物体分割;然后,以此为基础,生成输入图像的曲边网格表示;最后,通过对不同网格的非均匀缩放,生成符合目标尺寸的适配结果。结果在面向图像显示适配的公开数据集RetargetMe上,将本文方法与现有的10种代表性显示适配方法的结果进行了人工评估和比较。本文方法可以有效地减少显著物体出现部分扭曲的现象,能在48.8%的图像上取得无明显缺陷的适配效果,比现有最好的方法提高了5%。结论基于显著物体检测的图像显示适配方法有助于提高显示适配过程中对显著物体处理的一致性,减少由于显著物体部分扭曲而引起的明显人工处理痕迹,从而达到提升显示适配效果的目的。

Objective Image retargeting aims to automatically adjusl the resolnlion of an image by non-homogeneously scaling image content and displaying it in a limited screen with well-preserved salient objeets. A novel image retargeting method based on salient object detection is proposed to solve the partial distortion problem of salient objects. Method The proposed method utilizes the resuhs of salient object segmentation instead of saliency maps to improve retargeting performance. First, a saliency map is generated using saliency filsion and propagation strategy, which can ohtain the balance between the accacy and completeness of salient regions. Then, based on the inpnt image and saliency map, a saliency cut method with adaptive triple threshohling is adapted to segment salient objects, which can generate the salient objects with accurate boundaries. After this step, the curve-edge grid representation of the input image is constrncted hy finding the eight con- net,ted seams with the maximum energy. Finally, the grids ate non-unifiormlv scaled to satisfy the required size. Result Using manual evaluation, the performance of the proposed method are compared with those of ten typical ,nethods on RetargetMe dataset, a public dataset for image retargeting. Experimental results show that the proposed method can effcetively reduce the partial distortion of salient objects in image retargeting and obtain the retargeting results without obvious artifacts on 48. 8% images, a rate that is 5% better than the best existing image retargeting method. Conclusion The proposed image retargeting methods based on salient object segmentation can improve the consistency of salient object processing, reduce the obvious artifacts caused lay partial distortion of salient objects, and obtain good performaoce in retargeting.