CONTEXT
SALIENCY BASED IMAGE SUMMARIZATION
Liang Shi Jinqiao
Wang Hanqing Lu
Submitted to IEEE International Conference on Multimedia & Expo (ICME 2009)
ABSTRACT
The
problem of image summarization is to determine a smaller representation but
faithfully represent the original visual image appearance. In this paper, we
propose a context saliency based image summarization approach in a supervised
manner. Since merely visual saliency as importance measure is not enough, we
incorporate redundancy-based contrast analysis and geometric segmentation into context
saliency through naive Bayesian inference. Then we introduce a grid-based
piecewise linear image warping scaleplate to maintain the proportion of salient
objects. We argue that the image summaries should be appraised with target
device specification under perception constrains, and we adopt the sweet
spot evaluation to generate a flexible model that automatically combines
cropping and warping methods. Additionally, we explore potential extension on
multiple applications such as video retargeting, digital matting, image
browsing etc. Experimental results show comparable performance compared to the
state-of-art on common data sets.
METHOD
OVERVIEW
RESULTS
Scale
Change
1. Comparison with uniform scaling (From left to
right: original image; uniform scaling results; our results)
2. Comparison of visual saliency and context
saliency (From left to right: original image; uniform scale results; our
results)
3. Comparison
with other methods in image scale change (From left to right: original image;
uniform scale; Wolf 2007; Seam Carving; Wang 2008; Our results)
>
Thumbnail
Generation
Besides the original
image, the upper-right is generated by scaling and the lower-right is
summarized by our method.
Assisted
Image Editing
