as9993's profile - activity

Hi pi-null-mezon! Thank you for your answer. I forgot to mention, that I don't have a training set for every people i.e. the face is found only once so I cannot use a classical approach to this problem (with using a training set and train Eigenface algorithm to recognize the face and extract the vector of internal state of the algorithm). Should I use FaceRecognizer class for this task and if so, what training set I can use? Thank you! P.S. http://stackoverflow.com/a/7030545 (Here) is something useful, but I'm not sure if it's correct to use some example database for training and then pass the mine face that I extracted previously to the algorithm only to get the vector and then use this vector to calculate some metrics algorithm.

Hello! I use OpenCV with Python to detect faces in images (with Haar cascade detector). Everything work fine, but I have a question. How I can extract a face features and put them into vector or array? For example - I detect a face, get coordinates of the face in the image, extract the face, normalize it and then I want to extract the features that differs from face to face. For me doesn't matter what is exactly meaning of the integers from feature vector, I only want to be different between two faces. How I can done this? Any suggestions? BR, Alex