Scribd
Upload
104 views

Supervised Classification

This document provides instructions for performing supervised classification on an image to classify land use types. It involves displaying the image, creating signatures by drawing training samples for different land use classes like water, forest, urban and fallow land. The signatures are then used to alarm and classify the image using supervised classification, outputting a new classified image file. Additional training samples can be added and different classification rules tested to improve results.

Uploaded by

Pankaj Vishwakarma
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
104 views

Supervised Classification

This document provides instructions for performing supervised classification on an image to classify land use types. It involves displaying the image, creating signatures by drawing training samples for different land use classes like water, forest, urban and fallow land. The signatures are then used to alarm and classify the image using supervised classification, outputting a new classified image file. Additional training samples can be added and different classification rules tested to improve results.

Uploaded by

Pankaj Vishwakarma
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Supervised classification

Objective: To classify image using supervised technique and determine land use. 1. Display liss_57f2aoi.img in a viewer.

2. Goto Erdas Imagine Raster Tab, Supervised and select Signature editor. 3. Signature Editor dialog box get opens.

ERDAS Imagine Customer Education

-1-

4. Goto Drawing tab and select Polygon drawing tool in Insert Geometry section. 5. Draw a training sample eg. Water .

6. Goto Signature Editor and click Create signature from AOI.

7. Water body signature is added as Class1. 8. LMB in box under Color column and select the blue color. 9. LMB in box under Class Names and type Water. 10. Same way select some more training sample for Forest, Urban area and Fallow Land.

ERDAS Imagine Customer Education

-2-

11. After taking desired Classes your signature editor should look like this.

12. Save the signature file File- Save and save it by liss_4class.sig. 13. In the Signature Editor, select Waterbody by clicking in the > column for that signature. The alarm is performed with this signature. 14. In the Signature Editor Menu bar, select View -> Image Alarm The Signature Alarm dialog opens.

The alarmed pixels display in the Viewer in blue color. You can use the toggle function (SWIPE) in the Viewer to see how the pixels are classified by the alarm.
15. If required take more training sample and add in signature editor. 16. In Signature Editor click Classify-Supervised. 17. In Supervised Classification dialog, Specify the output file Name as liss_supervised.img and Non-parametric Rule: as Parallelepiped. 18. Click OK. 19. Change the Overlap and Unclassified rule and see the results in classified images.
ERDAS Imagine Customer Education

-3-

You might also like