Ameeer's profile - activity

overview network karma followed questions activity

2017-05-10 09:13:12 -0600	commented answer	LBPH training and test faces image size(Python) somehow ??
2017-05-08 07:00:07 -0600	commented answer	LBPH training and test faces image size(Python) Thanks i got a 92% of positive recognition now ! but still, the provided link of yours isn't in python, any hints where i can find the python copy of it ?!
2017-05-07 15:42:39 -0600	answered a question	Face Recognition Parameters Any idea ?
2017-05-07 15:37:43 -0600	commented answer	Face Detection Parameters Thanks a lot, thats was really helpful, one more thing, is theres any suggestions about the best values for theses parameters to choose ?
2017-05-07 15:32:54 -0600	asked a question	LBPH training and test faces image size(Python) Hello Its an easy question but i need the answer from people who tried it, should my training images be of the same size as my test images ? and if yes how could i do that in python3 and OpenCV3.2 ? one more thing, can you guide me to any easy guide to how to align face images without using OpenFace ? Thanks
2017-05-03 13:14:09 -0600	asked a question	Face Recognition Parameters Hello, am currently working with a face detection - recognition system, and currently am in the testing stage, but i am getting a bad recognition results either as a a)false positive (person X is identified as Person Y), b) negative (Person X is identified as Unknown), c) few positives (Person X is identified as Person X) I have searched a lot, and came to many important points. The training my case : i trained 50 face for each person, each face image was around [150150 to 200200] but i wasn't able to recognize any face that were 5050 or even 8080, how could i recognize them, more faces into training ? or what should i do ? I'm using python 3, OpenCV 3.2 and LBPH as recognizer. Thanks for your time.
2017-05-03 13:07:36 -0600	asked a question	Face Detection Parameters Hello, am currently working with a face detection - recognition system, and currently am in the testing stage, but i am confused with Detection phase I have searched a lot, and came to many important points. The detection i.e. `face_cascade.detectMultiScale(gray, 1.05, 3,minSize=(20, 20), maxSize=(200,200))` how should i choose, scaling factor, and how is it important (i didn't totally understood what its useful for though i read a lot ), and how to choose min. neighbors and the window size to ensure that i will be able later on to recognize these faces.
2017-05-03 13:04:53 -0600	commented question	Face recognition parameters okay delete this one and i will separate the question right away
2017-05-03 12:55:50 -0600	asked a question	Face recognition parameters Hello, am currently working with a face detection - recognition system, and currently am in the testing stage, but i am getting a bad recognition results either as a a)false positive (person X is identified as Person Y), b) negative (Person X is identified as Unknown), c) few positives (Person X is identified as Person X) I have searched a lot, and came to many important points. The detection i.e. `face_cascade.detectMultiScale(gray, 1.05, 3,minSize=(20, 20), maxSize=(200,200))` how should i choose, scaling factor, and how is it important (i didn't totally understood what its useful for though i read a lot ), and how to choose min. neighbors and the window size. 2.The training i.e. i use the same detection code to grap a new image and traing them, should i use same parameters too ? also how many faces per person should i take ? 5, 10 , 50 ?? one last thing is when i train lets say 50 image per person as a close image (200200), i can't detect that person almost at all if his face were sth around (100100), how could i solve this, should i train more image ? Thanks for your time and sorry if this is a long post.