Closed tomkwa closed 5 years ago
Duplicate of #1757 Train a new detector with other poses.
Warning: this issue has been inactive for 35 days and will be automatically closed on 2019-07-04 if there is no further activity.
If you are waiting for a response but haven't received one it's possible your question is somehow inappropriate. E.g. it is off topic, you didn't follow the issue submission instructions, or your question is easily answerable by reading the FAQ, dlib's official compilation instructions, dlib's API documentation, or a Google search.
Warning: this issue has been inactive for 42 days and will be automatically closed on 2019-07-04 if there is no further activity.
If you are waiting for a response but haven't received one it's possible your question is somehow inappropriate. E.g. it is off topic, you didn't follow the issue submission instructions, or your question is easily answerable by reading the FAQ, dlib's official compilation instructions, dlib's API documentation, or a Google search.
Notice: this issue has been closed because it has been inactive for 45 days. You may reopen this issue if it has been closed in error.
We are developing project where we need to set landmarks on frontal pose (0 degrees), left profile (90 degrees) and middle pose (45 degrees). DLIB out of the box has very good front face detector, but luck of the 2 more that we need. Our images that will be uploaded for lanmarking are standarized eg. whole face on white background. In theory we do need a detector to detect face, because face is the only item on the image. Being said that it will be easier (if possible) to force dlib to skip detector and try to use only shape predictor. Otherwise we need to develop profile detector and middle detector which is bigger thing to do... Is it possible? If anybody can give any hint I will be more than greatfull...