CH7 Representation & Description
CH7 Representation & Description
Object Recognition
How to represent an object shape?
Feature Extraction
How to describe the object
properties/characteristic?
OBJECT RECOGNITION
Object recognition systems find objects in the
real world from an image of the world.
2 0 4 0
5 7
3
6
4-directional 8-directional
converter converter
• These codes are also known as Freeman chain codes.
• Are used for the description of pixel border
• Local information of the objects can be obtained from the chain
code
– E.g. where image border turns 90 degrees etc.
• Follow a clockwise direction and assigning a direction to the
segments connecting every pair of pixels.
• The chain code of a boundary depends on the starting point.
• Unacceptable for 2 principal reasons;
1) The resulting chain code tends to be quite long
2) Any small disturbance along the boundary due to noise or
imperfect segmentation cause changes in the code that may not
be related to the principal shape features of the boundary.
Example 1:
2
3 1
1
4 0
2 0
5
3 7
6
4-directional 8-directional
converter converter
OBJECT Start with the start point and go along
START the arrows
Comparing the boundary of object with
respect to 4-directional chain code
converter, we get
Chain code of Object: 03032211
Difference Code:
Difference code:
30101033003100030300013003
Shape Number:
00013003301010330031000303
8-directional Chain Code
3 2 1
4 0
5 6 7
0 0 0 0 0 0
2 7
3 7
3 6
4 4 4 4 4 6
Exercise:
Obtain the chain code for 8-direction converter
More Exercises:
(a) Obtain the chain code (b) Obtain the chain code
(c) Obtain the object shape based on the following chain code
• 000066644422
• 00777444666552222221
FEATURE EXTRACTION: