How observant are you?
How observant are you?
How observant are you?
face recognition
One of the oldest forms of identification is photo ID. What is it about the face that makes it easy to recognize?
A computer program can detect a face by looking for a pair of eyes, for example.
What if we had a three-dimensional model of the face? A special camera, called a range camera, can capture range measurements and construct a 3D face model.
2018 was the year of face recognition. Watch this short documentary to know why:
What things about the face cannot be easily changed?
The location of the eyes, nose, mouth and chin depend on the skull and jaw. If a face is level with eyes open and mouth closed, these locations can be easily compared. Since bones are internal and rigid, these measurements can help identify a person.
then, we use measurements and maths to compare faces.
what are some of the measurements that are useful?
Eyes distance
Nose width
Eyes depth
cheek bones shape
jaw line length
Go to GOOGLE CLASSROOM and do the activity.
Face recognition is useful for crime solving, but it also has commercial applications. Have any of you used Picasa for sharing pictures on the internet? It has face detection, and if you label some pictures of a person with a name, it can find other pictures or that person. Pretty cool, huh? Some photo editors also include face detection to let people create wacky images for fun
Face recognition is useful for crime solving, but it also has commercial applications. Have any of you used Picasa for sharing pictures on the internet? It has face detection, and if you label some pictures of a person with a name, it can find other pictures or that person. Pretty cool, huh? Some photo editors also include face detection to let people create wacky images for fun
1. Using a picture of your face, mark the corners of your eyes and your mouth and the tip of your nose.
2. Fill in the chart to measure distances and compute ratios (normalized distances).
label points:
A B C D
E
F G
H
Denominator AD=_______ Measurement Normalized, divided by AD
Distance AB (eye width)
Distance BC (between eyes)
Distance FG (mouth width)
Distance AE
Distance EH
Distance AF
Assume symmetry. Assume E and H are on a line bisecting and perpendicular to line segment AD. With that assumption, one other distance is enough to locate E and H (why?). If we assume EH is perpendicular to FG and bisects FG, then distance AF is enough to locate the mouth (why?). Compare normalized measurements. Why do we normalize the data?
(This activity is an idea from kidsahead.com)