As lejlot correctly mentioned, SVM cannot be trained with variable length vectors.
You can just normalize image size to one, i.e. 256x256. There are 3 possibilities to do this:
- Crop the 256x256 patch around center.
- Resize image to 256x256 discarding original aspect ratio.
- Resize image to 256xM where M < 256 - preserving original aspect ratio. Than add grey stripes at left and right (or top and bottom) to fill image to the 256x256.
All variants are used by different authors and you have to check which one suits your task best.