Cracking the Leaf Code with Computer Vision

Add event to my Google calendar Add event to my Google calendar Share this event on facebook E-mail this event
Wednesday, May 04, 2016 4:00pm - 5:00pm
Watson CIT - SWIG Boardroom (CIT241)

Thomas Serre
Manning Assistant Professor
Cognitive, Linguistic and Psychological Sciences 

 

Cracking the Leaf Code with Computer Vision

Leaves are the most conspicuous and abundant plant parts, but until now, the vast quantity of evolutionary information encoded in their complex, variable shapes, and venation patterns was largely inaccessible. Machine vision offers opportunities to analyze large numbers of specimens, to discover novel leaf features of angiosperm clades that may have phylogenetic significance, and to use those characters to classify unknowns. In this talk, I will report on our progress towards the development of a machine vision system for automated leaf classification. The current system uses cleared leaf specimens that are chemically bleached, then stained to reveal venation. I will present results showing that the system can accurately categorize thousands of angiosperm leaf images into natural botanical groups, visually representing a wealth of novel botanical characters.

Hosted by Dan Weinreich