By: Suvigya Tripathi (09BEC094) Ankit V. Gupta (09BEC106) Guided By: Prof. Bhupendra Fataniya Dept. of Electronics and Communication Engineering, Nirma University at Ahmedabad. REVIEW-1

 What is face detection.  The History.  Challenges.  2D-Image Scan.  Biometrics : Skin Texture Analysis.  Applications.

 Steps:  Face Detection: differentiate a human face from the background of the image or a real time video.  Feature Detection: record its features.  Face Recognition: Compare it to a data base.

 Technique employed to distinguish a Human face from the rest of the background of the image.

 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.

 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)

 In – Plane Rotation  Out – Plane Rotation  Lighting  Aging Effects  Facial Expressions  Face Covered by long Hairs or Hand.

 Different Approaches: ◦ Knowledge Based Approach ◦ Feature Invariant Method ◦ Template Matching Method

 It uses human-coded rules to model facial features, such as two symmetric eyes, a nose in the middle and a mouth underneath the nose.

 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  Cons: ◦ 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

 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.

 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 o The length of the jaw line

 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 background

 Template matching methods calculate the correlation between a test image and a pre-selected facial templates.

 Pros: ◦ Simple  Cons: ◦ Templates needs to be initialized near the face images ◦ Difficult to enumerate templates for different poses (similar to knowledge-based methods)

 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.

 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.

 Security measure at ATM’s  Digital Cameras  Public Surveillance (CCTV’s) at Airports, Hospitals, etc.  Televisions and computers can save energy by reducing the brightness.

 A set of two task:  Face Identification: Given a face image that belongs to a person in a database, tell whose image it is.  Face Verification: Given a face image that might not belong to the database, verify whether it is from the person it is claimed to be in the database.

 Wikipedia.org  How Stuff Works   Kimmel, Ron. "Three-dimensional face recognition". Retrieved "Three-dimensional face recognition"  Ziyou Xiong, Univ. of Illinois at Urbana-Champaign