The Community for Technology Leaders
2015 IEEE International Conference on Computer Vision (ICCV) (2015)
Santiago, Chile
Dec. 7, 2015 to Dec. 13, 2015
ISSN: 2380-7504
ISBN: 978-1-4673-8390-5
pp: 100-108
In many fine-grained object recognition datasets, image orientation (left/right) might vary from sample to sample. Since handcrafted descriptors such as SIFT are not reversal invariant, the stability of image representation based on them is consequently limited. A popular solution is to augment the datasets by adding a left-right reversed copy for each original image. This strategy improves recognition accuracy to some extent, but also brings the price of almost doubled time and memory consumptions. In this paper, we present RIDE (Reversal Invariant Descriptor Enhancement) for fine-grained object recognition. RIDE is a generalized algorithm which cancels out the impact of image reversal by estimating the orientation of local descriptors, and guarantees to produce the identical representation for an image and its left-right reversed copy. Experimental results reveal the consistent accuracy gain of RIDE with various types of descriptors. We also provide insightful discussions on the working mechanism of RIDE and its generalization to other applications.
Training, Object recognition, Image representation, Birds, Histograms, Indexes, Feature extraction

L. Xie, J. Wang, W. Lin, B. Zhang and Q. Tian, "RIDE: Reversal Invariant Descriptor Enhancement," 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 100-108.
239 ms
(Ver 3.3 (11022016))