I want to extract salient region from large set of images but as I experienced, some salient region detectors are not fast enough. Is there any good algorithm that is capable of processing images fast and gives relatively good results (at least some heuristic) for salient regions of images?
Ussually those are rather quick. Hence I assume your input images are of relatively high resolution. You might want to downscale them before processing with saliency alogorithms (and obvioulsly upsacaling the result). Depending on what you want to do with the saleint regions, this might even give nicer results. If this is not what you want, you might want to clarify what you mean by large data set, what you would consider a reasonable time and at which scale you regions of interest are.
Jan
This answer has been quoted from Prof. Jim Peters:
"Salient image regions in both low and high resolution images can be detected in a satisfactory manner, provided we define saliency in terms of "sufficient nearness".
To do this, we need to consider the original suggestion by Alt in 1962 and define a similarity distance between sets of picture points (identified with picture regions). A region that is close enough to a region-of-interest would be considered salient. This approach to saliency should work, independent of image resolution."
- Badges
- Science topic
- Similar topics
- Engineering
- Electrical Engineering
- Signal Processing
- Image Processing