Hello
I'm working on a project that I want to detect forest and deforestation areas. I need some information about Maximum-likelihood or Support vector machine (SVM) for image classification.
If you have multispectral image (R,G, B and NIR bands) then you can apply NDVI to distinguish between vegetation and non-vegetation areas easily.
For supervised learnin like SVM you may try using pixels values as inputs for each classes for traning and testing. If it doesnot work, then you may need to extract some extra features like textural features and they see if it works.
A general intorudction to SVM can be found in
https://towardsdatascience.com/https-medium-com-pupalerushikesh-svm-f4b42800e989#:~:text=At%20first%20approximation%20what%20SVMs,separates%20those%20classes%20if%20possible.
A sample paper for application of SVM for vegetation/land cover classification is
https://ieeexplore.ieee.org/abstract/document/8063324
Pythong pacakge contaning SVM is available in
https://scikit-learn.org/stable/supervised_learning.html#supervised-learning
Have a look at https://www.ingentaconnect.com/content/asprs/pers/2004/00000070/00000012/art00002?crawler=true&mimetype=application/pdf
https://au.mathworks.com/help/stats/support-vector-machines-for-binary-classification.html
- Badges
- Science topic
- Similar topics
- Computer Science
- Images