Image Classification
Image Classification
Image classification
• Image classification: is the process by which pixels
which have similar spectral characteristics and which are
consequently assumed to belong to the same class are
identified and assigned a unique colour.
•Digital image classification is the process of assigning
pixels to classes.
• For the first part of the classification process, the
computer system must be trained to recognize patterns
in the data.
• Training is the process of defining the criteria by which
these patterns are recognized.
2
Image classification
Objective: Convert
image data into
thematic data
3
Land cover map
Classified
Ikonos image
April 2000
Enschede
Applications ????
4
Image space
A digital image is a 2D-array of pixels.
The value of a pixel - the DN - is in the
case of 8 bits recording in the range 0 to
255. A DN corresponds to the energy
reflected or emitted from a ground
resolution cell.
6
Feature space
A graph that shows the feature vectors is
called a feature space, or ‘feature space
plot’ or ‘scatter plot’.
7
Multi-dimensional feature space
8
Scatter plot
9
10
•There are two ways to classify pixels into different
categories:
unsupervised classification
supervised classification
•Unsupervised classification: it is a technique that
groups the pixels into clusters based upon the
distribution of the digital numbers in the image.
• The classes that result from unsupervised
classification are spectral classes. Because they are
based solely on the natural grouping in the image
values.
11
Supervised classification
Supervised classification is the process of
using samples of known identity to classify
pixels of unknown identity.
13
Image classification process
• Classification Steps
1.It is always a good reference to first perform an
unsupervised classification.
• This gives a general impression of the classes
involved.
2. Define Training Areas
3. Run Supervised Classification
4. Additional Classification by Editing
5. Accuracy Assessment
15
• Supervised Classification Algorithms
i. Minimum Distance to Mean Classifier: every pixel is
assigned a class based on its distance from the mean of
each class.
• Also called spectral distance classifier.
16
ii.
Parallelepiped (box) Classifier: the data file values
of the candidate pixel are compared to upper and
lower limits. These limits can be either:
the minimum and maximum data file values of each band
in the signature,
the mean of each band, plus and minus a number of
standard deviations, or
any limits that you specify, based on your knowledge of the
data and signatures.
17
iii. Maximum Likelihood Classifier: assumes a
normal distribution for the training areas.
• Also called the Bayesian classifier.
• Probability contours are created around each
training area and a pixel assigned to a class
depending upon the value of the probability
contours that encompass it.
• The maximum likelihood classifier is generally
considered to be the most powerful but is also
considered the most computer intensive.
18
Maximum Likelihood Classifier
19
• False color Landsat-TM
• Classified Landsat-TM
20
Accuracy assessment
• Accuracy assessment is a general term for
comparing the classification to geographical
data that are assumed to be true.
•From the accuracy assessment cell array, two
kinds of reports can be derived:
The error matrix simply compares the reference points
to the classified points in a cxc matrix, where c is the
number of classes.
The accuracy report calculates statistics of the
percentages of accuracy, based upon the results of the
error matrix.
Once the sampling has been carried out, an error matrix can be established
Other terms for this table are confusion matrix or contingency matrix.
21
Accuracy assessment
Error of omission: refers to those pixels
which are wrongly classified to other classes.
water bodies