Page tree
Skip to end of metadata
Go to start of metadata

This fish dataset currently consisting of 3,960 images collected from 468 species. This data consists of real-world images of fish captured in conditions defined as "controlled", "out-of-the-water" and "in-situ". The "controlled", images consists of fish specimens, with their fins spread, taken against a constant background with controlled illumination. The "in-situ" images are underwater images of fish in their natural habitat and so there is no control over background or illumination. The "out-of-the-water" images consist of fish specimens, taken out of the water with a varying background and limited control over the illumination conditions. A tight red bounding box is annotated around the fish. 





This data are used for WACV 2014 paper "Local Inter-Session Variability Modelling for Object Classification".  Baseline classification results can also be found in this paper.

Download link can be used as follows (Dropbox):

or (BaiduYun)


Send email to zongyuan ge  ( or to request for the dataset. (respond in 24 hours)

Please cite this: 

  title={Local inter-session variability modelling for object classification},
  author={Anantharajah, Kaneswaran and Ge, ZongYuan and McCool, Christopher and Denman, Simon and Fookes, Clinton B and Corke, Peter and Tjondronegoro, Dian W and Sridharan, Sridha},



Dataset Authors

ZongYuan Ge     or

Dr Chris Mccool 

Prof Peter Corke          peter.corke at


Please direct any dataset queries or issues to ZongYuan Ge.