packages icon
A. Etemadi, ICSTM, Feb 17th 1993

These directories contain the elements for creating, testing, and running 
the Object Recogition Toolkit (ORT). Contact me (address at the end of
this file) if you have any problems.

*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*
       INSTALL file contains Installation info.
       The Doc/FAQ file contains frequently asked questions and usage info. 
       The Doc/EXAMPLE file contains an example session
       The Doc/PHILOSOPHY file describes the philosophy behind the design
*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*

         ============================================
         Object Recognition Toolkit (ORT) Version 2.3
         ============================================

ORT is a collection of pixel grouping S/W in C aimed for use on Unix
platforms (Sun4, Decstation, Iris, X86 under Linux). Currently the 
starting point for ORT is an edge detected image. The S/W is in the 
form of filters and includes a displayer for use on COLOUR workstations 
under X11R4/5. All the S/W comes with the GNU general public licence. 
Also included are LaTeX copies of papers on some of the S/W (FEX, LPEG). 
Basically ORT allows you to create progressively more complex groupings 
of a set of edge pixels [lines/arcs -> parallel/collinear/junctions ->
triplets/corners/polygons]. Changes from previous versions are:

Version 2.1:
   1. All programs are now default driven
   2. PGM format as standard with option for raw images
   3. Added new options to LPEG and IPEG
   4. IPEG is fully general and very much faster
   5. LPEG now has option to consider pairs of collinear lines as real lines

Version 2.3:
   1. Changed names of programs and converted to lowercase characters
   2. Added support for rectangular images
   3. Fixed problem with HUGE value being too big for some compilers (eg
      gcc on 386 and 486PCs.)
   4. Now all programs (except ort2image) may be chained using Unix pipes
   5. The ID number assigned to Lines and Circular arcs is constant. Before I 
      used to change ID numbers when grouping the lines. This caused some
      people problems.
   6. All programs are faster (specially ipeg).
   7. Fixed problem (actually a C bug I think :) in ipeg which made it give
      segmentation fault for no reason. This was due the use of bcopy.
      Now only if you set the quality factor very low (eg 0.3) it usually 
      requires too much memory for average machines and crashes. Since I don't 
      know how to check for available memory on-the-fly I left this bug alone.
   8. Restructured the directories

The features defined within ORT represent the complete set required to 
recognize any polyhedral object (view point independently) starting from edge 
information. Available later this year will be an Edge detection module,
and hopefully also a generalised curve grouping system.

    Code                              Description
--------------     ----------------------------------------------------------
Liste              List handling library in C by Jean-Paul Schmidt formerly
                   of University of Surrey, UK. [Version 1.2]

chainpix           Pixel Chainning code by Geoff A.W. West and Paul L. Rosin
                   of Curtin University, Australia [Version 1.2]

fex                Segments chained pixel lists produced by chainpix
                   into straight-line segments and circular arcs. [Version 1.7]

lpeg               Low-level straight-line grouping [Version 1.9]. Groups 
		     straight-line segments produced by fex into:

                         Parallel overlapping   Parallel non-overlapping
                         Collinear              V,L,T, and Lambda Junctions

ipeg               Intermediate-level grouping [Version 2.1]. Groups sets 
		     produced by lpeg into:

                         Triplets (barends, Z)
                         Corners  (3 lines sharing a junction point)
                         Polygons 

DisplayGrps        X11R4/5 viewer for the above groupings/segments by
                   Jean-Paul Schmidt and Ata Etemadi [Version 1.2]

I would appreciate it if people who obtain the S/W drop me a line. All
contributions/comments to the distribution are most welcome. If you have
any problems I'll be glad to help.

       regards
                Ata <(|)>.

| Mail          Dr Ata Etemadi, Blackett Laboratory,                          |
|               Space and Atmospheric Physics Group,                          |
|               Imperial College of Science, Technology, and Medicine,        |
|               Prince Consort Road, London SW7 2BZ, ENGLAND                  |
| Phone         +44 (0)71 589 5111 Ext 6751 or 6752 (secretary/answer phone)  |
| Fax           +44 (0)71 823 8250 Attn. Dr Ata Etemadi,                      |
| Telex         929484 (IMPCOL G)  Attn. Dr Ata Etemadi,                      |
| Janet                        atae@uk.ac.ic.ph.spva or ata@uk.ac.ucl.mssl.c  |
| Internet/Arpanet/Earn/Bitnet atae@spva.ph.ic.ac.uk or ata@c.mssl.ucl.ac.uk  |
| Span                              SPVA::atae       or     MSSLC:atae        |
| UUCP/Usenet                       atae%spva.ph.ic@nsfnet-relay.ac.uk        |