1 | initial version |
As I couldn't found any proper classifier that is capable of detecting side-way faces,
please have a look at this
then, the whole idea of "synthesizing" multiple positive images from one or a few is broken, and won't work.
(your blog/tutorial seems quite outdated, please use this instead
instead,
opencv_createsamples -vec faces.vec -info info.txt -w 24 -h 24
2 | No.2 Revision |
As I couldn't found any proper classifier that is capable of detecting side-way faces,
please have a look at this
then, the whole idea of "synthesizing" multiple positive images from one or a few is broken, and won't work.
(your blog/tutorial seems quite wrong and outdated, please use this instead )
instead,
opencv_createsamples -vec faces.vec -info info.txt -w 24 -h 24
3 | No.3 Revision |
As I couldn't found any proper classifier that is capable of detecting side-way faces,
please have a look at this
then, the whole idea of "synthesizing" multiple positive images from one or a few is broken, and won't work.
(your blog/tutorial seems quite wrong and outdated, please use this instead )
instead,
opencv_createsamples -vec faces.vec -info info.txt -w 24 -h 24
4 | No.4 Revision |
As I couldn't found any proper classifier that is capable of detecting side-way faces,
please have a look at this
then, the whole idea of "synthesizing" multiple positive images from one or a few is broken, and won't work.
(your blog/tutorial seems quite wrong and outdated, please use this instead )
instead,
opencv_createsamples -vec faces.vec -info info.txt -w 24 -h 24
5 | No.5 Revision |
As I couldn't found any proper classifier that is capable of detecting side-way faces,
please have a look at this (the general problem with profile views is, that you can train it only for one side, and you have to flip() the image, and try a detection for both sides later)
then, the whole idea of "synthesizing" multiple positive images from one or a few is broken, and won't work.
(your blog/tutorial seems quite wrong and outdated, please use this instead )
instead,
opencv_createsamples -vec faces.vec -info info.txt -w 24 -h 24
6 | No.6 Revision |
As I couldn't found any proper classifier that is capable of detecting side-way faces,
please have a look at this (the general problem with profile views is, that you can train it only for one side, and you have to flip() the image, and try a detection for both sides later)
then, the whole idea of "synthesizing" multiple positive images from one or a few is broken, and won't work.
(your blog/tutorial seems quite wrong and outdated, please use this instead )
instead, so, try:
opencv_createsamples -vec faces.vec -info info.txt -w 24 -h 24