Seam warping: a new approach for image retargeting for small displays

Abstract

Image retargeting is a technique to adapt an image to display on devices with different sizes and aspect ratios. When mobile devices with small displays are increasingly popular, it becomes important to retarget images that are intended for regular monitors to smaller mobile screens. Existing methods that retarget images to smaller devices, such as seam carving and warping, have some limitations: seam caving method may damage the integrity of the image, and warping method could fail when focus detection algorithm is not good. The target images obtained through the above algorithms often have obvious distortions. In this paper, we propose a new image retargeting method that combines seam caving and warping. This method preserves the advantage of warping in keeping focused areas of the image without discarding unfocused contents, and at the same time, uses seam finding scheme to address the problem of focus detection. The results of our experiment study on user preferences of retargeted images show that our approach is successful for image retargeting.

Structure preservation in content‐aware image retargeting using multi‐operator

“…In this, the image retargeting run‐time of MO6 has been compared with the five published conventional image retargeting techniques, viz. seam carving (SC) [1], stretch and scale (SNS) [10], seam warping (SW) [38], warp [5], and MO [9]. This MO is a combination of SC with scaling, cropping, and warping and hence is quite similar to our proposed MO6.…”

“…In the next step, warping is applied. Zhang et al [38] combined SC and warping in which SC detected ROIs by considering seams with maximum energy and warping retargeted the image. Dong et al [39] suggested a retargeting approach that used different approaches for textured and non‐textured regions.…”

Seam Manipulator: Leveraging Pixel Fusion for Depth-Adjustable Stereoscopic Image Retargeting

“…In future work, we plan to consider additional depth-adjustable properties (e.g., vergence and accommodation) simultaneously. We also plan to extend this framework to enable new role in discrete and continuous approaches [52].…”

A Survey on Content Aware Image Resizing Methods

“…They also proposed an optional step to accelerate the seam carving process. Zhang et al [93] proposed a new multi-operator image resizing to combine seam caving and warping image retargeting operators. The proposed method safeguard the benefits of warping operators in keeping highly noticeable areas of the image without dumping contents of the image which are unnoticeable.…”