[Taxacom] Automated species Identification by Image Analysis

[Dr. David Campbell]

As a participant in some non-automated species identification by image 
analysis (i.e., "Send in your photos and we'll get someone to identify 
them"), I would note that image quality is a major issue.  Scale is a 
useful bit of information often omitted by the general public.  On the 
other hand, it's usually safe to assume in that context that the organism 
in question is large by invertebrate standards.

Automated species identification by image analysis for someone with 
specimen in hand and where the identification does not depend on 
dissection or other additional processes should be fairly straightforward.  
Identification of random photos of something seen outside is rather more 
challenging for a computer.

-- 
Dr. David Campbell
425 Scientific Collections Building
Department of Biological Sciences
Biodiversity and Systematics
University of Alabama, Box 870345
Tuscaloosa AL 35487-0345  USA