1 | initial version |
Hi,
1.In case of 2 different views of the same object. If there is a big differnce in the object apearence it is recommnded to train 2 calssifiers. Yet if there is no such a big difference in the object apearence you may train only one classifier. Anyway try and you'll find out what is the best for you.(You may supply images and I'll tru to recomend based on them)
2.The positive images may be color or grey it doesn't matter ,since the algortihm uses only the grey values and ignores the color information. The reason for that is that color information change heavily under different lighting conditions.
Good luck,
2 | No.2 Revision |
Hi,
1.In case of 2 different views of the same object.
If there is a big differnce in the object apearence apearance it is recommnded to train 2 calssifiers.
two classifiers.
Yet if there is no such a big difference in the object apearence apearance you may train only one classifier.
Anyway try and you'll find out what is the best for you.(You may supply you.(Post some positive images and I'll tru try to recomend based on them)recommend )
2.The positive images may be color or grey gray it doesn't matter ,since the algortihm uses only the grey gray values and ignores the color information.
The reason for that is that color information change heavily under different lighting conditions.
Good luck,