3. The Error Matrix
01
02
03
04
The classification scheme becomes a
very important factor influencing the
accuracy of the entire project.
Differences between the remotely
sensed map and the reference data.
Variation in human interpretation is
often very difficult to control.
There are a number of methods that
try to go beyond the basic error
matrix.
5. ADVANTAGE
The accuracy of
the classification
can increase
dramatically.
DISADVANTAGE
The reason for
accepting plus or
minus one class
cannot be
adequately
justified.
1. Modifying
the Error
Matrix
The simplest method. This method
works well if the classification is
continuous such as tree size
class or forest crown closure.
6. This table presents the traditional error
matrix for a classification of forest crown
closure. Only exact matches are considered
correct and are tallied along the major
diagonal.
Tabel 7.1 Error Matrix Showing the Ground
Reference Data versus the Image Classification
for Forest Crown Closure
7. This table presents the same error matrix, only
the major diagonal has been expanded to
include plus or minus one crown closure class.
Tabel 7.2 Error Matrix Showing the Ground
Reference Data versus the Image
Classification for Forest Crown Closure within
Plus or Minus One Tolerance Class
8. Education
Plan
2. Fuzzy Set Theory
Fuzzy logic recognizes that, an item on the margins of
classes may belong to both classes.
The use of these fuzzy rules, which allow for
acceptable answers as well as absolutely correct
answers, makes a great deal of sense.
Fuzzy set theory working for
continuous variables such as crown
closure, it also applies to more
categorical data.
fuzzy as away to characterize the ability
of the human brain, but difficult task
in using fuzzy logic is the development
of rules for its application.
9. This table presents off-diagonal elements in the
matrix contain two separate Values. This is
combination of absolutely correct and
acceptable answers results.
Tabel 7.3 Error Matrix Showing the Ground
Reference Data versus the Image Classification
for Forest Crown Closure Using the Fuzzy Logic
Rules
10. Education
Plan
3. Measuring Variability
Measure
Each
Reference
Measure
the
Variance
Measure the variation and to use
the measurements to compensate
for differences between reference
and map data that are caused not
by map error but by variation in
interpretation. To reduce variance in
reference site labels.
Prohibitively expensive.
Usually requiring
extensive file sampling.
To compensate for non-
error differences between
references and map data.
Time consuming and
expensive.
Must evaluate each
accuracy assessment site.
12. Change Detection
how does one obtain information on
the reference data for images that
were taken in the past? or
how can one sample enough areas
that will change in the future?
All change detection techniques
use a threshold value to
determine which pixels have
changed from those pixels that
have not changed.
Because all of the cells of the
matrix are considered, the
Kappa coefficient of agreement
was the recommended measure
of accuracy.
13. Figure 7.2
a comparison between a single classification
error matrix and a change detection error
matrix for the same vegetation/land use
categories.
What category was this area
at time 1 and what is it at
time 2?
The answer has nine possible
outcomes for each dimension
of the matrix : (A at time 1
and A at time 2, A at time 1
and B at time 2, A at time 1
and C at time 2, …, C at time
1 and C at time 2).
we are no longer looking at a single classification, but rather a Change between two differe
nt
classiFications generated at different times.
14. Accuracy assessments
have been performed
on each of the map
layers and each layer
is 90% accurate.
Figure 7.3
The range of accuracies for a
decision made from combining
multiple layers of spatial data.
If the four map layers
are not independent,
the accuracy of the
final map is 90%.
Certainly this
knowledge can help us
to improve our ability to
effectively use spatial
data.
Multilayer
Assessments
If the four map layers
are independent, the
accuracy of the final
map is 90% × 90% ×
90% × 90% = 66%.