Untagged regions could then be sent to the recognition engine/script and be tagged automatically after. With the things implemented in the first point, it should be possible to extract the faces/regions from already tagged photos and train the face recognitioner. This way, you can use a person name/tag and tag photo regions. Further, a tag shall be associatable to that selected region (that would not only allow faces, but other details to be selected - as flickr allows it). user could select a frame as done for selection now), and digikam would store this information somewhere in the database. The user OR a program would say where the the faces are (e.g. The simple / first thing I think should be implemented is face detection and face outline display in digikam. The second is to recognize the face at the detected region and say who it is. The first is to actually detect the position and region of a face, or all the faces on the photo. There are two things: Face detection and face recognition. OK, I will stop at this point, maybe someone else has more luck.
Presumably all this will require some more digging in the original opencvĪlso note that the libface project does not appear that active,Īfter an initial check-in 6 weeks ago nothing happened. The region of interest with a face to be recognized is not clear to me. Then there is ellip-mask.jpg which provides a mask, maybe(?) usedįor the input images. (note to self: don't use my own pictures, but those of models, So far I only managed to get a segmentation fault. Presumably it is train followed by recognize or facedetect.įor train one has to supply a file which contains names and
#DIGIKAM FACE RECOGNITION TUTORIAL HOW TO#
I missed something) documentation how to use these: However, it is not clear from the (essentially lacking, unless Then one has to look in the examples directory of libface-0.1,Ĭonstructmat.cpp facedetect.cpp recognize.cpp train.cpp (I can post more details on that if needed). Then libface needs some tweaking in the header files so that opencv is found,īut compiles fine after that. I had a quick look at installing opencv (which fortunately exists Well, this will be a long road until success: My girlfriend and I use it since years, and it's been unvaluable for managing our photo collection. And by the way, thanks for making digikam. It would be very cool if digkam would get such a feature. If it gets that, it'll be my personal killer feature to use fspot.
#DIGIKAM FACE RECOGNITION TUTORIAL CODE#
Gnome's F-Spot will get this feature trough the summer of code project. libFace is another one that specializes in face rec/det and uses intel's lib internally. There are some face detection and recognition libraries out there that could be used, one well-known is the Intel's OpenCV lib. What I would like to see is a plugin that automatically detects faces and allows one to drag a tag from the tag tree on, or just add a tag to the detected face. Tags help here, but not all photos are tagged through the reason above. When searching for photos, you often try to find a person - how it looked at a time, or generally need all photos of a certain person. While setting tags for a whole album (france, wedding, 2007) is easy and fast to do, tagging each of the 200+ photos in an album with the people on it is impossible. Tagging photos by hand is not doable anymore since it takes too much time.
0 kommentar(er)
