Slayt 1

1
Date 13.12.2005 Submitted to Dr.
Atilla Elci Submitted by Fatih Dikili
2
Representation and recognition To recognise
individual objects in a digital image, there are
two problems that need to be solved given a
collection of named objects, construct a computer
representation or model of each object, and
given a digitized sensor image (intensity or
range data, for example), find either or all of
the following 1. an identity or name,
2. the location, and 3. the orientation of
each object in the scene.
3
(No Transcript)
4
Modelling Scope and uniqueness Stability and
sensitivity 1.wire frame, 2.Constructive Solid
Geometry, 3.spatial occupancy techniques surface
boundary representations, for example polygons,
B-splines, or Bezier surfaces etc.
Object recognition ?Transformation of image
?Matching of perspective ?use of the Artificial
Intelligence ?Adequate information related to
necessary objects kept in DB
5
What About Path Recognition??
Self-learning Path Recognition
1-PATH INTEGRATION 2-IMAGE MATCHING
6
Figure 2. Navigation System Overview
--64x64 gray-scale image --Highlightening
mechanism --resolution reduction mechanism
7
REFERENCES

• http//homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_C
  OPIES/OWENS/LECT13/lect13.html
• http//www-formal.stanford.edu/jmc/whatisai/whatis
  ai.html