Oleg Zabluda's blog
Friday, September 28, 2012
 
Cat snout detection in JavaScript from Microsoft Research (not Viola-Jones, for a change) (via Sergei Burkov)
Cat snout detection in JavaScript from Microsoft Research (not Viola-Jones, for a change) (via Sergei Burkov)

http://harthur.github.com/kittydar/

"""
In this paper, we choose to be conservative and limit our endeavor to ... cat head detection. This is of course not a random selection. ... First, cat can represent a large category of cat-like animals, ... Second, people love cats. A large amount of cat images have been uploaded and shared on the web. For example, 2,594,329 cat images had been manually annotated in flickr.com by users. Cat photos are among the most popular animal photos on the internet. Also, cat as a popular pet often appears in family photos...Third, given the popularity of cat photos, it is easy for us to get training data. The research community does need large and challenging data set to evaluate the advances of the object detection algorithm. In this paper, we provide 10,000, well labeled cat images.
"""

https://github.com/harthur/kittydar
http://research.microsoft.com/pubs/80582/ECCV_CAT_PROC.pdf
http://137.189.35.203/WebUI/CatDatabase/catData.html
http://research.microsoft.com/pubs/80582/ECCV_CAT_PROC.pdf

Labels:



Powered by Blogger