Patch-Based Image Warping for Content-Aware Retargeting

Abstract

Abstract-Image retargeting is the process of adapting images to fit displays with various aspect ratios and sizes. Most studies on image retargeting focus on shape preservation, but they do not fully consider the preservation of structure lines, which are sensitive to human visual system. In this paper, a patch-based retargeting scheme with an extended significance measurement is introduced to preserve shapes of both visually salient objects and structure lines while minimizing visual distortions. In the proposed scheme, a similarity transformation constraint is used to force visually salient content to undergo as-rigid-as-possible deformation, while an optimization process is performed to smoothly propagate distortions. These processes enable our approach to yield pleasing content-aware warping and retargeting. Experimental results and a user study show that our results are better than those generated by state-of-the-art approaches.

Content-Aware Image Retargeting Incorporated with Letterboxing

“…The width of these images is 768 or 800 pixels and was reduced by half in a retargeting process. The proposed method was compared with the two conventional warping methods, optimized scale-and-stretch resizing (SS) [9] and patch-based image warping (PB) [12]. In addition, the proposed method was also compared with multi-operator retargeting (MO) [17] which uses three operators (cropping, scaling and seam carving).…”

“…The second advantage is free from bending of grid lines. Whereas some researches [9], [12] require an energy term which penalizes grid edge orientations to prevent excessive grid line bending, the proposed approach is free from bending of grid lines in principle.…”

“…This method has suitable characteristics for retargeting because it detects the image regions that represent the scene, which differs from methods whose goal is to detect the dominant object. Conventional retargeting methods such as [12], [28] use [27] for computation of an importance map. Importance A crop range is calculated based on the image importance S .…”

Perceptually Guided Photo Retargeting

“…Simple photo cropping does not work when esthetically pleasing regions are dispersely distributed in a photo. Toward an optimal retargeting result, most of the existing works focus on content-aware photo retargeting [1], [13], [16], [18], [22], aiming at maximally preserving visually salient regions while keeping the nonsalient ones to a minimum scale. However, the existing content-aware photo retargeting algorithms suffer from the following two drawbacks.…”

Gradient-based global features for seam carving

“…Seam carving is an approach to image retargeting that has greater flexibility than cropping and resampling and holds a simple algorithm besides [2,3]. Although several retargeting methods have been developed, such as mesh-deformation-based techniques [4][5][6] and some combinations of multiple methods [7], seam carving still remains an effective tool due to the simplicity and the scalability. Seam carving has expanded in applications, such as for video sequences [8], stereo images [9], image compression [10,11], tamper detection [12,13], and particular images having high image detail concentration [14].…”