Journal
VISION RESEARCH
Volume 187, Issue -, Pages 55-65Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.visres.2021.06.007
Keywords
Texture; Natural image statistics; Higher-order statistics; Computational modeling; Segmentation
Categories
Funding
- National Institutes of Health [EY031166]
- Comision Academica de Posgrados, UdelaR, Uruguay
- PEDECIBA, UdelaR, Uruguay
- CSIC, Uruguay
Ask authors/readers for more resources
The study reveals that both spectral statistics and higher-order statistics (HOS) can be used for texture segmentation tasks in natural images, but combining them does not significantly improve segmentation performance. Different subsets of HOS may have varying effects on segmentation results, although the improvement from HOS in some images is difficult to identify.
Visual texture, defined by local image statistics, provides important information to the human visual system for perceptual segmentation. Second-order or spectral statistics (equivalent to the Fourier power spectrum) are a well-studied segmentation cue. However, the role of higher-order statistics (HOS) in segmentation remains unclear, particularly for natural images. Recent experiments indicate that, in peripheral vision, the HOS of the widely adopted Portilla-Simoncelli texture model are a weak segmentation cue compared to spectral statistics, despite the fact that both are necessary to explain other perceptual phenomena and to support high-quality texture synthesis. Here we test whether this discrepancy reflects a property of natural image statistics. First, we observe that differences in spectral statistics across segments of natural images are redundant with differences in HOS. Second, using linear and nonlinear classifiers, we show that each set of statistics individually affords high performance in natural scenes and texture segmentation tasks, but combining spectral statistics and HOS produces relatively small improvements. Third, we find that HOS improve segmentation for a subset of images, although these images are difficult to identify. We also find that different subsets of HOS improve segmentation to a different extent, in agreement with previous physiological and perceptual work. These results show that the HOS add modestly to spectral statistics for natural image segmentation. We speculate that tuning to natural image statistics under resource constraints could explain the weak contribution of HOS to perceptual segmentation in human peripheral vision.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available