[R] image recognition in R

Barry Rowlingson B.Rowlingson at lancaster.ac.uk
Thu Aug 26 13:17:30 CEST 2004


> Angel wrote:
>  > > I have some images of bugs (insects) with many bugs in each image.
>  > > I want to count the number of bugs and to have an estimate of 
>  > > the area of each one.
>  > > I've tried searching for an R package to do so with no 
>  > > success. Is this a task that I should pursue doing in R or 
>  > > should I restrict myself to specific image analysis software 
>  > > (e.g. ImageJ)?.
>  > > 
>  > > The reason I consider R would be a good choice is because 
>  > > then It would probably be possible to use R statistical power 
>  > > to do pattern recognition on each bug's image to try to 
>  > > identify each bug (Family, genus or species).
>  > > Is anybody working in this direction?

I see people have mentioned ImageJ, but I recently discovered the 
UTHSCSA Image Tool (http://ddsdx.uthscsa.edu/dig/itdesc.html) which does 
lots of image processing things. Its free, the source code is available 
(it says, the ftp link is bad though), and one of the examples is in 
classifying black 'blobs' in an image.

  It has the power to export various quantities for each identified 
object (major/minor axis, size, perimeter, that sort of thing) so you 
could import that into R for more discrimination. Not seamless, but 
workable.

  Beware though, it did crash _lots_ when were doing object identification.

Barry




More information about the R-help mailing list