This Article 
 Bibliographic References 
 Add to: 
Low-Level Hierarchical Multiscale Segmentation Statistics of Natural Images
Sept. 2014 (vol. 36 no. 9)
pp. 1900-1906
Emre Akbas, Department of Psychological and Brain Sciences, University of California Santa Barbara, Santa Barbara,
Narendra Ahuja, Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana,
This paper is aimed at obtaining the statistics as a probabilistic model pertaining to the geometric, topological and photometric structure of natural images. The image structure is represented by its segmentation graph derived from the low-level hierarchical multiscale image segmentation. We first estimate the statistics of a number of segmentation graph properties from a large number of images. Our estimates confirm some findings reported in the past work, as well as provide some new ones. We then obtain a Markov random field based model of the segmentation graph which subsumes the observed statistics. To demonstrate the value of the model and the statistics, we show how its use as a prior impacts three applications: image classification, semantic image segmentation and object detection.
Index Terms:
Image segmentation,Histograms,Computational modeling,Vectors,Image edge detection,Markov processes,Gray-scale,Markov random field,Natural image statistics,low-level hierarchical segmentation
Emre Akbas, Narendra Ahuja, "Low-Level Hierarchical Multiscale Segmentation Statistics of Natural Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 9, pp. 1900-1906, Sept. 2014, doi:10.1109/TPAMI.2014.2299809
Usage of this product signifies your acceptance of the Terms of Use.