Importance filtering for image retargeting

Ding, Yuanyuan; Xiao, Jing; Yu, Jingyi

doi:10.1109/cvpr.2011.5995445

Cited by 94 publications

(45 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When p i and p are in a flat region, d geo (p, p i ) = 0 and S(p, p i ) = 1, ensuring that p i adds a unit area to the area of p. When p i and p are in different regions, there exists at least one strong edge (d app ( * , * ) 3σ clr ) on their shortest path and S(p, p i ) ≈ 0, ensuring that p i does not contribute to p's area. Experimentally, we find that the performance is stable when parameter σ clr is within [5,15]. We set σ clr = 10 in the experiments.…”

Section: Effective Computationmentioning

confidence: 99%

See 1 more Smart Citation

Saliency Optimization from Robust Background Detection

Zhu

Liang

Wei

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

1,153

805

View full text Add to dashboard Cite

Recent progresses in salient object detection have exploited the boundary prior, or background information, to assist other saliency cues such as contrast, achieving stateof-the-art results. However, their usage of boundary prior is very simple, fragile, and the integration with other cues is mostly heuristic. In this work, we present new methods to address these issues. First, we propose a robust background measure, called boundary connectivity. It characterizes the spatial layout of image regions with respect to image boundaries and is much more robust. It has an intuitive geometrical interpretation and presents unique benefits that are absent in previous saliency measures. Second, we propose a principled optimization framework to integrate multiple low level cues, including our background measure, to obtain clean and uniform saliency maps. Our formulation is intuitive, efficient and achieves state-of-the-art results on several benchmark datasets.

show abstract

Section: Effective Computationmentioning

confidence: 99%

“…It is motivated by the importance of saliency detection in applications such as object aware image retargeting [5,11], image cropping [13] and object segmentation [20]. Due to the absence of high level knowledge, all bottom up methods rely on assumptions about the properties of objects and backgrounds.…”

Section: Introductionmentioning

confidence: 99%

Saliency Optimization from Robust Background Detection

Zhu

Liang

Wei

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

1,153

805

View full text Add to dashboard Cite

show abstract

“…Continuous warping has been used in many image retargeting algorithms [4,7,10,11,24]. The basic idea is to deform the original image to the target image through a continuous transformation, which is estimated by image content.…”

Section: Related Workmentioning

confidence: 99%

Scale and object aware image retargeting for thumbnail browsing

Sun

Ling

2011

2011 International Conference on Computer Vision

View full text Add to dashboard Cite

Many image retargeting algorithms, despite aesthetically carving images smaller, pay limited attention to image browsing tasks where tiny thumbnails are presented. When applying traditional retargeting methods for generating thumbnails, several important issues frequently arise, including thumbnail scales, object completeness and local structure smoothness. To address these issues, we propose a novel image retargeting algorithm, Scale and Object Aware Retargeting (SOAR), which has four components: (1) a scale dependent saliency map to integrate size information of thumbnails, (2) objectness (Alexe et al. 2010) for preserving object completeness, (3) a cyclic seam carving algorithm to guide continuous retarget warping, and (4) a thinplate-spline (TPS) retarget warping algorithm that champions local structure smoothness. The effectiveness of the proposed algorithm is evaluated both quantitatively and qualitatively. The quantitative evaluation is conducted through an image browsing user study to measure the effectiveness of different thumbnail generating algorithms, followed by the ANOVA analysis. The qualitative study is performed on the RetargetMe benchmark dataset. In both studies, SOAR generates very promising performance, in comparison with state-of-the-art retargeting algorithms.

show abstract

“…This is due to their advantages against traditional eye fixation models [1,2,3,4] on applications, e.g. contentbased image cropping [5], thumbnailing [6], resizing and retargeting [7,8]. For such applications, salient object detection has evolved to uniformly highlight an object.…”

Section: Introductionmentioning

confidence: 99%