Professional Documents
Culture Documents
Face Detection&Rec
Face Detection&Rec
Face Detection&Rec
OUTLINE
What
is face detection.
The
Applications.
2
INTRODUCTION
Steps:
INTRODUCTION
Face interface
Face
Face database
Output:
Mr.Chan
Face recognition Prof..Cheng
employed to distinguish a Human face from the rest of the background of the image.
5
A picture has 0,1 or many faces Faces are not the same: with spectacles, mustache etc Sizes of faces vary
THE HISTORY
During 1964 and 1965, Bledsoe, along with Helen Chan and Charles Bisson , worked on using the computer to recognize human faces. He was proud of this work, but because the funding was provided by an unnamed intelligence agency that did not allow much publicity, little of the work was published.
7
The first step for any automatic face recognition system system. First step in many Human Computer Interaction systems. Expression Recognition Cognitive State/Emotional State Recognition First step in many surveillance and security systems. Video coding Automatic Target Recognition(ATR)
8
CHALLENGES
In Plane Rotation Out Plane Rotation Lighting Aging Effects Facial Expressions Face Covered by long Hairs or Hand.
CHALLENGES
10
2D IMAGE SCAN
Different Approaches: Knowledge Based Approach Feature Invariant Method Template Matching Method
11
KNOWLEDGE-BASED APPROACH
It uses humancoded rules to model facial features, such as two symmetric eyes, a nose in the middle and a mouth underneath the nose.
12
KNOWLEDGE-BASED APPROACHSUMMARY
pros: Easy to come up with simple rules Based on the coded rules, facial features in an input image are extracted first, and face candidates are identified Work well for face localization in uncluttered background
con: Difficult to translate human knowledge into rules precisely: detailed rules fail to detect faces and general rules may find many false positives Difficult to extend this approach to detect faces in different poses: implausible to enumerate all the possible cases
13
Feature invariant methods try to find facial features which are invariant to pose, lighting condition or rotation. Skin colors, edges and shapes fall into this category.
14
Every face has numerous, distinguishable landmarks, the different peaks and valleys that make up the face o Distance between the eyes o Width of the nose o Depth of the eye sockets o The shape of the cheekbones
15
Pros: Features are invariant to pose and change in orientation. Cons: Difficult to locate facial features due to several corruption (illumination, noise, occlusion) Difficult to detect features in complex
16
Template matching methods calculate the correlation between a test image and a preselected facial templates.
17
Pros: Simple Cons: Templates needs to be initialized near the face images Difficult to enumerate templates for different poses (similar to knowledge-based methods)
18
Using skin color to find face segments is a vulnerable technique. Non-animate objects with the same color as skin can be picked up since the technique uses color segmentation. Then the face can be picked up using any of the approaches.
19
SKIN TEXTURE ANALYSIS: ADVANTAGES Lack of restriction to orientation or size of faces. A good algorithm can handle complex backgrounds. It is relatively insensitive to changes in expression, including blinking, frowning or smiling Has the ability to compensate for mustache or beard growth and the appearance of eyeglasses.
20
Detection rate Give positive results in locations where faces exist Should be high > 95% False positive rate The detector output is positive but it is false (there is actually no face).Definition of False positive: A result that is erroneously positive when a situation is normal. An
example of a false positive: a particular test designed to detect cancer of the toenail is positive but the person does not have toenail cancer. (http://www.medterms.com/script/main/art.asp?articlekey=3377) Should be low <10-6
A good system has High detection rate Low false positive rate
21
EXERCISE
What are the detection rate and false detection rate here?
9 faces in the picture, 8 are correctly detected.
Answer
detection
22
Integral
image for feature extraction Ada-Boost for feature selection Attentional cascade for fast rejection of non-face sub-windows
23
Rectangle_Feature_value f=
(pixels in white area) (pixels in shaded area)
24
EXERCISE
Find the Rectangle_Feature_val ue (f) of the box enclosed by the dotted line
Rectangle_Feature_value f= (pixels in white area) (pixels in shaded area) f=(8+7)-(0+1) =15-1= 14
1 3 5
2 0 8
3 1 7
3 3 1
25
Result
This is a face:T he eye-part is dark, the nose-part is bright So f is large, hence it is face This is not a face. Because f is small
26
HOW TO FIND FEATURES FASTER INTEGRAL IMAGES FAST CALCULATION METHOD [LAZEBNIK09 ]
The integral image = sum of all pixel values above and to the left of (x,y) Can be found very quickly
(x,y)
27
28
ii(x, y-1)
s(x-1, y)
i(x, y)
Cumulative row sum: s(x, y) = s(x1, y) + i(x, y) Integral image: ii(x, y) = ii(x, y1) + s(x, y)
29
A,B,C,D are the values of the integral images at the corners of the rectangle R. The sum of image values inside R is: Area_R = A B C + D If A,B,C,D are found , only 3 additions are needed to find Area_R
30
WHY DO WE NEED TO FIND PIXEL SUM OF RECTANGLES? ANSWER: WE WANT TO GET FACE FEATURES
31
-1 216 102 78 Integral White area Image 129 210 111 +2 F=Feat_val = pixel sum in shared area - pixel sum in white area Example Pixel sum in white area= 216+102+78+129+210+111=846
Pixel sum in shared area= 10+20+4+7+45+7=93 Feat_val=F=846-93 If F>threshold, feature=+1 Else feature=-1 End if; We can choose threshold =768 , so feature is +1.
A face
32
(1,1)
X-axis 1280
Set (x,y) = the left top corner of the 24x24 sub-window For the 24x24 sub-window, extract 162,336 features and see they combine to form a face or not. }
Yaxis
1024
33
Boosting
Combine
34
35
AdaBoost training
E.g. Collect 5000 faces, and 9400 non-faces. Different scales. Use AdaBoost for training to build a strong classifier. Pick suitable features of different scales and positions, pick the best few. (Take months to do , details is in [Viola 2004] paper)
Testing
Scan through the image, pick a window and rescale it to 24x24, Pass it to the strong classifier for detection. Report face, if the output is positive
36
In the paper it shows that the following two features (obtained after training) in cascaded picked by AdaBoost have 100% detection rate and 50% false positive rate I.e. But 50% false positive rate is not good enough H(face)= Approach [viola2004] :Attentional cascade Sign{1h1(image)
+2h2(image)} Pick a window in the image and rescale it to 24x24 as image
H(face)=+1 face H(face)=-1non-face
h1(image) type2
h2(image) type3
37
A 200-feature classifier can yield 95% detection rate and a false positive rate of 1 in 14084 (Still not god enough) Recall: False positive rate The detector output is positive but it is false (there is actually no face). Definition of False positive: A result that is erroneously positive when a situation is normal. An example of a false positive: a particular test designed to detect cancer of the toenail is positive but the person does not have toenail cancer. (http://www.medterms.com/script/main/art.asp?articlekey=3377)
Cascade of many AdaBoost strong classifiers Begin with with simple classifiers to reject many negative sub-windows Many non-faces are rejected at the first few stages. Hence the system is efficient enough for real time processing.
Adaboost Classifier1
Input image
True
Adaboost Classifier2
True
Face found
False Non-face
False Non-face
39
AN EXAMPLE
10 features
25 features
50 features
True
Adaboost Classifier2
True
Face found
False Non-face
False Non-face
40
ATTENTIONAL CASCADE
Chain classifiers that are progressively more complex and have lower false positive rates:
% Detection
True
Adaboost Classifier2
True
Face found
False Non-face
False Non-face
41
Adaboost Classifier2
Face found
False Non-face
False Non-face
42
scale
the detection (not the input image) Features evaluated at scales by factors of 1.25 at each level Location : move detector around the image (1 pixel increments)
Final detections
A
real face may result in multiple nearby detections (merge them to become the final result)
43
FACE RECOGNITION
2009 TotallyLooksLike.com
Security measure at ATMs Digital Cameras Public Surveillance (CCTVs) at Airports, Hospitals, etc. Televisions and computers can save energy by reducing the brightness.
APPLICATIONS
46