CIPA 2003 XIX th International Symposium, 30 September - 04 October, 2003, Antalya, Turkey
300
Pixel based classifications
Object based classifications
^ □ Pixel ^
Unsupervised
Supervised
classification
classification
Pixel
<
Multivariate
▼
segmentation
Label
assignement
Mini.
distance
Maximum
likelihood
Nearest
Neighbour
1
r 1
r
1
r
Rules (object
features + class
related features)
a) Isodata
classification
wrm
li.
b) Min. distance
classification
S J W :
«û—ûfl?
»
c) Max. likelihood
classification
d) Nearest Neighbour
sample based
classification
¿à-:
e) Rule based
classification
Caption :
□ tiled roof; HI oak wood beams; □ facing (masonry); El freestone; □ shutter; □0 sky
Figure 3. Flow chart of all experiments and results achieved
4.2. Rule-based classification
In this part, a higher degree of image analysis is applied. The
most delicate and also interesting work consists in developing
rules describing and formalising the knowledge on
characteristics of Alsatian façades. These rules can integrate
various object features (spectral values, shape, texture,
hierarchy, etc.) or class related features (relation to neighbour
objects, sub-objects, etc.) which are furthermore defined by
membership functions. In these membership functions one
can introduce fuzzy logic by particularly weighting that
feature and combining it through logical operators with other
features.
For instance, to discriminate sky from the rest of the image,
one use the particularity that sky brightness is stronger than
the brightness of the rest of the image. Another characteristic
is that the standard deviation of the sky is especially small.
Result is shown in Fig.4.
Figure 4. Rules established for the discrimination
of the class “sky” (blue)
