fengtianliang's profile - activity

Now I extract the geometric feature from people face,as following picture show: I mark the interesting points,as follow: I calculate the distance between (s5,s6),(s1,s2),(s1,s7),(s2,s7),(s3,s7),(s4,s7),then divide by the distance from the midpoint of s1 and s2 to the midpoint of s3 and s4. I want to use the distance ratio to classify the faces,because I think the faces belong to the same person,the above distances will be nearness.

Unfortunately this way is not OK,and can not classify faces belong to different people,the different people's face,the above distance may also be nearness.

Now How can I use the geometric feature to do this work.

Looking forward to your reply！

Best Regards!

I will to develop a app to classify photos by people's face,that is to say the photos belongs to the one same person will put together.I have a idea:first i extract the facial feature of the photos which contain the eyes、nose、mouth,second compare the feature vector and return the similarity of the two photo.Now my problem is how to compare the feature vector? Any help will be appreciated!

hi Elias Rammos: If I set the threshold to 3000.some trained person'faces can not be recognize,so the threshold must be appropriate. Do you know how to calculate the threshold ?

hi everyone: Opencv FaceRecognition have 2 phase:training and predicting,After training, In the first phase,we trained 2 persons s1 and s2, s1/1.pgm;0 s1/2.pgm;0 s1/3.pgm;0 s1/4.pgm;0 s2/1.pgm;1 s2/2.pgm;1 s2/3.pgm;1 s2/4.pgm;1 then in the seconde phase,if I predict s1/5.pgm(whichever belong to person s1),i can get the label 0 and it is correct. if I predict s3/5.pgm(which is a face of a new person),the predicting result may be 0 or 1 but no -1,and it is wrong!

I want to know when the I can get -1 by using predict method or how can I know the face belong to a new person?

Look foward to your soonest reply! Thanks!