A histogram semantic-based distance for multiresolution image classification

Abstract : Image classification methods based on histogram analysis generally require to use relevant distances for histogram comparison. In this article, we propose a new distance devoted to compare histograms associated to semantic concepts linked by (dis)similarity correlations. This distance, whose computation relies on a hierarchical strategy, captures the multilevel semantic relations between these concepts. It also inherits from the low complexity properties of standard bin-to-bin distances, thus leading to fast and accurate results in the context of multiresolution image classification. Experiments performed on satellite images emphasize the relevance and usefulness of the proposed distance.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.univ-reims.fr/hal-01695060
Contributor : Nicolas Passat <>
Submitted on : Thursday, February 15, 2018 - 11:57:33 AM
Last modification on : Thursday, July 19, 2018 - 3:34:01 PM
Long-term archiving on : Tuesday, May 8, 2018 - 12:21:55 AM

File

Kurtz_ICIP_2012.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Camille Kurtz, Nicolas Passat, Pierre Gançarski, Anne Puissant. A histogram semantic-based distance for multiresolution image classification. International Conference on Image Processing (ICIP), 2012, Orlando, United States. pp.1157-1160, ⟨10.1109/ICIP.2012.6467070⟩. ⟨hal-01695060⟩

Share

Metrics

Record views

88

Files downloads

93