Image orientation detection using LBP-based features and logistic regression

Many imaging applications require that images are correctly orientated with
respect to their content. In this work we present an algorithm for the automatic detection of
the image orientation that relies on the image content as described by Local Binary Patterns
(LBP). The detection is efficiently performed by exploiting logistic regression. The pro-posed algorithm has been extensively evaluated on more than 100,000 images taken from the
Scene UNderstanding (SUN) database. The results show that our algorithm outperformed
similar approaches in the state of the art, and its accuracy is comparable with that of human
observers in detecting the correct orientation of a wide range of image contents.

RESULTS

 

SOURCE CODE and DATA

  orientation-mta-dist.tar.gz (2.7 MiB, 588 hits)

Publications

1.

Image orientation detection using LBP-based features and logistic regression
(Gianluigi Ciocca, Claudio Cusano, Raimondo Schettini) In Multimedia Tools and Applications, volume 74, number 9, pp. 3013-3034, Springer US, 2015.

@article{ciocca2013image-orientation,
 author = {Ciocca, Gianluigi and Cusano, Claudio and Schettini, Raimondo},
 year = {2015},
 pages = {3013-3034},
 title = {Image orientation detection using LBP-based features and logistic regression},
 volume = {74},
 number = {9},
 publisher = {Springer US},
 journal = {Multimedia Tools and Applications},
 pdf = {/download/ciocca2013image-orientation.pdf},
 doi = {10.1007/s11042-013-1766-4},
 issn = {1573-7721}}