NCBI ROFL: Introducing…the automatic LOLcat detector!

By ncbi rofl | February 17, 2011 7:00 pm

Detecting Some Popular Animals in Online Photos: Learning from Ears and Eyes.

“Robust object detection has many important applications in real-world online photo processing. For example, both Google image search and MSN live image search have integrated human face detector to retrieve face or portrait photos. Inspired by the success of such face filtering approach, in this paper, we focus on another popular online photo category – animal, which is one of top five categories in the MSN live image search query log. As a preliminary attempt, we focus on the problem of animal head detection of a set of relatively large land animals that are popular on the internet, such as cat, tiger, panda, fox, and cheetah. First, we proposed a new set of gradient oriented feature, Haar of Oriented Gradients (HOOG), to effectively capture the shape and texture features on animal head. Then, we proposed two detection algorithms, namely Bruteforce detection and Deformable detection, to effectively exploit the shape feature and texture feature simultaneously. Experiment results on 14,379 well labeled animals images validate the superiority of the proposed approach. Additionally, we apply the animal head detector to improve the image search result through text based online photo search result filtering.”

Bonus figure:

Fig. 12: Detection results on the cat data set.

Photo: icanhascheezburger

Related content:
Discoblog: NCBI ROFL: Two Cute: Research that would make grad school snugglier
Discoblog: NCBI ROFL: Think all cows look alike? Then clearly you’re not a cow
Discoblog: NCBI ROFL: Behavioural responses of dogs to asymmetrical tail wagging of a robotic dog replica.

WTF is NCBI ROFL? Read our FAQ!

NEW ON DISCOVER
OPEN
CITIZEN SCIENCE
ADVERTISEMENT

Discover's Newsletter

Sign up to get the latest science news delivered weekly right to your inbox!

Discoblog

Quirky, funny, and surprising science news from the edge of the known universe.

About ncbi rofl

NCBI ROFL is the brainchild of two Molecular and Cell Biology graduate students at UC Berkeley and features real research articles from the PubMed database (which is housed by the National Center for Biotechnology information, aka NCBI) that they find amusing (ROFL is a commonly-used internet acronym for "rolling on the floor, laughing"). Follow us on twitter: @ncbirofl

ADVERTISEMENT

See More

ADVERTISEMENT
Collapse bottom bar
+

Login to your Account

X
E-mail address:
Password:
Remember me
Forgot your password?
No problem. Click here to have it e-mailed to you.

Not Registered Yet?

Register now for FREE. Registration only takes a few minutes to complete. Register now »