based on the idea that a user can select sample pixels in an image that are representative of specific classes and then direct the image processing software to use these training sites as references for the classification of all other pixels in the image.
- The operator can spot mistakes and often corrects them.
- The analyst does not have to worry about matching categories on the final map to field data.
- The process is completely within the control of the analyzer.
- Specific sections of known identity are linked to processing.
- the class s defined by the Analyst
- gathering training for different class is very difficult and time consuming
- the unrepresented place in training data is difficult to recognize
- needs very clear training process
- and also requires labelled data set
The computer uses techniques to determine which pixels are related and groups them into classes. The user can specify which algorism the software will use and the desired number of output classes but otherwise does not aid in the classification process.
- It is not necessary to label the training data set.
- it is time saving process
- fast classification
- Along the classification process, there is no concept of output.
- It is not possible to estimate or map the outcome of a new sample.
- In the presence of outliers, the outcome varies greatly.
these are the basic and major advantages and disadvantage of supervised and unsupervised image classification