TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

ABSTRACT

Facial recognition (or face recognition) is a type of biometric software application that can identify a specific individual in a digital image by analyzing and comparing patterns. Facial recognition systems are commonly used for security purposes but are increasingly being used in a variety of other applications. For example, Face book uses facial recognition software to help automate user tagging in photographs

DEPT.OF ECE

Page 1

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

CHAPTER 1 INTRODUCTION

DEPT.OF ECE

Page 2

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

Humans are very good at recognizing faces and if computers complex patterns. Even a passage of time doesn't affect this capability and therefore it would help become as robust as humans in face recognition. Machine recognition of human faces from still or video images has attracted a great deal of attention in the psychology, image processing, pattern recognition, neural science, computer security, and computer vision communities. Face recognition is probably one of the most non-intrusive and userfriendly biometric authentication methods currently available; a screensaver equipped with face recognition technology can automatically unlock the screen whenever the authorized user approaches the computer. Face is an important part of who we are and how people identify us. It is arguably a person's most unique physical characteristic. While humans have had the innate ability to recognize and distinguish different faces for millions of years, computers are just now catching up. Visionics, a company based in New Jersey, is one of many developers of facial recognition technology. The twist to its particular software, FaceIt, is that it can pick someone's face out of a crowd, extract that face from the rest of the scene and compare it to a database full of stored images. In order for Face Recognition

Technology software to work, it has to know what a basic face looks like. Facial recognition software is designed to pinpoint a face and measure its features. Each face has certain distinguishable landmarks, which make up the different facial features. These landmarks are referred to as nodal points. There are about 80 nodal points on a human face. Here are a few of the nodal points that are measured by the software: Distance between eyes Width of nose Depth of eye sockets Cheekbones Jaw line Chin

DEPT.OF ECE

Page 3

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

These nodal points are measured to create a numerical code, a string of numbers that represents the face in a database. This code is called a face print. Only 14 to 22 nodal points are needed for the Face It software to complete the recognition process. Facial recognition (or face recognition) is a type of biometric software application that can identify a specific individual in a digital image by analyzing and comparing patterns. biometric is a unique, measurable characteristic of a human being that can be used to automatically recognize an individual or verify an individual identity. Biometrics can measure both physiological and behavioral characteristics. Physiological biometrics (based on measurements and data derived from direct the human body) include: 1.Finger-scan , 2.FacialRecognition, 3.Iris-scan , 4.Retina-scan 5..Hand-scan.

Behavioral biometrics (based on measurements and data derived from an action) include: 1.Voice-scan , 2.Signature-scan 3. Keystroke-scan . 1.1 FACE RECOGNITION: The face is an important part of who you are and how people identify you. For face recognition there are two types of comparisons.

DEPT.OF ECE

Page 4

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

1. verification. 2. identification. 1.11 VERIFICATION: It is where the system compares the given individual with who that individual says they are and gives a yes or no decision.. 1.12 IDENTIFICATION: It is where the system compares the given individual to all the Other individuals in the database and gives a ranked list of matches.

All identification or authentication technologies operate using the following four stages: 1. Capture: A physical sample is captured by the system during enrollment and also in
identification or Verification process.

2. Extraction: unique data is extracted from the sample and a template is created. 3. Comparison: the template is then compared with a new sample.

4. Match/Non match: the system decides if the features extracted from the new

The image is optical in characteristics and may be thought of as a collection of a large number of bright and dark areas representing the picture details. In other words the picture information is a function of two variables: Time and Space.

DEPT.OF ECE

Page 5

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

It would require infinite number of channels to transmit optical information corresponding to picture elements simultaneously. There is practical difficulty in transmitting all information simultaneously so we use a method called scanning. Facial recognition software is based on the ability to first recognize faces, which is a technological feat in itself. If you look at the mirror, you can see that your face has certain distinguishable landmarks. These are the peaks and valleys that make up the different facial features. There are about 80 nodal points on a human face. Here are few nodal points that are measured by the software. 1.2 PERFORMANCE: 1.False rejection rates (FRR) : The probability that a system will fail to identify an enrollee. It is also called type 1 error rate. FRR= NFR/NEIA Where FRR= false rejection rates NFR= number of false rejection rates NEIA= number of enrollee identification attempt 2. False acceptance rate (FAR) : The probability that a system will incorrectly identify an individual or will fail to reject an imposter. It is also called as type 2 error rate

FAR= NFA/NIIA Where FAR= false acceptance rate NFA= number of false acceptance NIIA= number of imposter identification attempts
DEPT.OF ECE Page 6

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

CHAPTER 2 SYSTEM BLOCK DIAGRAM AND ITS DESCRIPTION

DEPT.OF ECE

Page 7

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

The following graphic illustrates the Face Detection system:

In the first step the system uses an adaptive pre-filter to eliminate candidate rectangles in the input that it can confidently determine do not contain faces. In the second step the system feeds the remaining rectangles to an improved implementation of an algorithm called Boosting Chain. Boosting Chain is a framework for rapid object detection developed by Microsoft Research (please see the Documentation section below for a paper detailing Boosting Chain). Finally, in the third step the system attempts to eliminate false positives. It

applies a color filter and an edge filter to improve the precision of the detection. It uses a support vector machine (SVM) filter, plus lighting correction and histogram equalization, to further eliminate false positives. The system then outputs each

rectangle, which contains a detected face, along with its confidence in each detection.
DEPT.OF ECE Page 8

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

Components The Face Detection algorithm can be divided into three parts: 1. Pre-filtering stage: This stage includes pre-color filters and non-face skipping algorithm. 2. Boosting filtering stage 3. Post-filtering stage: This part includes SVM classifier, Edge boosting filter, postcolor filter and eye component filter.

Face Detection algorithm structural overview:

Input image
If in-plane detection feature enabled
Preprocessing Pre-filtering boostingfiltering Post-filtering

Compute integral image for color filter and boosting filter

Compute two rotated integral image for color filter and boosting filter

CrCb pre-color filter for frontal faces Non-face skip filter

RGB pre-color filter for profiled/ tilted/ext faces Non-face skip filter

RGB pre-color filter for profiled/ tilted/ext faces Non-face skip filter

RGB pre-color filter for profiled/ tilted/ext faces Non-face skip filter

Boosting Chain classifier for frontal faces

Ext Boosting Chain classifiers for frontal faces

2 Boosting Chain classifiers for profile faces

2 Boosting Chain classifiers for tilted faces

CrCb post-color filter for frontal faces

RGB post-color filter for profiled/ tilted/ext faces

RGB post-color filter for profiled/ tilted/ext faces

RGB post-color filter for profiled/ tilted/ext faces

Eye filter

SVM filter

Eye filter

Eye filter

Eye filter

SVM filter

Edge filter

Edge filter

Merge

Final Output

DEPT.OF ECE

Page 9

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

In order to simplify the face detection problem, the system divides the target faces to be detected into four categories: upright frontal face, extend frontal face set with difficulty illumination/lighting and expression, profiled face (left profile and right profile), and in-plane rotated face (clockwise and anti-clockwise). Three sets of filters are applied to each kind of face. After the filtering stage, regions detected are merged to generate final result.

DEPT.OF ECE

Page 10

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

CHAPTER 3 DEVELOPMENT OF SOFTWARE

DEPT.OF ECE

Page 11

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

3.1 FACIAL RECOGNITION SOFTWARE:

It falls into a larger group of technologies known as biometrics. Biometrics uses
biological information to verify identity. The basic idea behind biometrics is that our bodies contain unique properties that can be used to distinguish us from others. Besides facial recognition, biometric authentication methods also include: "Fingerprintscan "Retinascan " Voice identification Facial recognition methods generally involve a series of steps that serve to capture, analyze and compare a face to a database of stored images. The basic processes used by the FaceIt system to capture and compare images are: 1.Detection - When the system is attached to a video surveillance system, the recognition software searches the field of view of a video camera for faces. If there is a face in the view, it is detected within a fraction of a second. A multi-scale algorithm is used to search for faces in low resolution. The system switches to a high-resolution search only after a head-like shape is detected. 2. Alignment - Once a face is detected, the system determines the head's position, size and pose. A face needs to be turned at least 35 degrees toward the camera for the system to register it. 3. Normalization -The image of the head is scaled and rotated so that it can be registered and mapped into an appropriate size and pose. Normalization is performed regardless of the head's location and distance from the camera. Light does not impact the normalization process.

4. Representation - The system translates the facial data into a unique code. This coding process allows for easier comparison of the newly acquired facial data to stored facial data. 5. Matching - The newly acquired facial data is compared to the stored data and (ideally) linked to at least one stored facial representation.

DEPT.OF ECE

Page 12

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

The Face Detection technique is mature and well tested on a large scale dataset. Still image detection prototype screenshot:

DEPT.OF ECE

Page 13

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

CHAPTER 4 APPLICATIONS

DEPT.OF ECE

Page 14

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

There are numerous applications for face recognition technology:

4.1 COMMERCIAL USE:

a. Day Care: Verify identity of individuals picking up the children. b. Residential Security: Alert homeowners of approaching personnel c. Voter verification: Where eligible politicians are required to verify their identity d. Banking using ATM: The software is able to quickly verify a customer.

4.2 GOVERNMENT USE:

a. law enforcement: Minimizing victim trauma verifying identify for court records, and comparison school surveillance camera images to know child molesters. b. security/counterterrorism: access control, comparing surveillance images to know terrorist. c. immigration: rapid progression through customs. d. voter identification: where eligible politicians are required to verify their identity during a voting process this is intended to stop proxyvoting where the vote may not go as expected.

DEPT.OF ECE

Page 15

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

CHAPTER 5 ADVANTAGES AND DISADVANTAGES

DEPT.OF ECE

Page 16

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

5.1 Advantages :
1. There are many benefits to face recognition systems such as its convenience and Social acceptability. All you need is your picture taken for it to work.

2. Face recognition is easy to use and in many cases it can be performed without a Person even knowing.

3. Face recognition is also one of the most inexpensive biometric in the market and Its price should continue to go down.

5.2 Disadvantages:
1. Face recognition systems cant tell the difference between identical twins.

DEPT.OF ECE

Page 17

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

CHAPTER 6 CONCLUSIONS AND FUTURE SCOPE

DEPT.OF ECE

Page 18

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

6.1 Conclusion:
Face recognition technologies have been associated generally with very costly top secure applications. Today the core technologies have evolved and the cost of equipments is going down dramatically due to the integration and the increasing processing power. Certain applications of face recognition technology are now cost effective, reliable and highly accurate. As a result there are no technological or financial barriers for stepping from the pilot project to widespread deployment.

6.2 Futurescope:
Face recognition technologies have been associated generally with very costly top secure applications. Today the core technologies have evolved and the cost of equipment is going down dramatically due to the integration and the increasing processing power. Certain applications of face recognition technology will be effective, reliable and highly accurate in future. cost

DEPT.OF ECE

Page 19

TECHNICAL REPORT

FACE RECOGNITION TECHNOLOGY

BIBILIOGRAPHY

1. Rong Xiao, Mingjing Li, Hongjiang Zhang. Robust Multipose Face Detection in Images . IEEE Transactions on Circuits and Systems for Video Technology (CSVT), Volume 14, PART1, 2004.

2. Longbin Chen, Lei Zhang, Hongjiang Zhang, and Mohamed Abdel-Mottaleb. 3D Shape Constraint Facial Feature Localization Using Probabilistic-like Output. Accepted by 6th IEEE International Conference on Automatic Face and Gesture Recognition (FG), Seoul, Korea, 2004.

3. Longbin Chen, Lei Zhang, Long Zhu, Mingjing Li and Hongjiang Zhang, A Novel Facial Feature Point Localization algorithm using Probabilistic-like output , in Proc. of Asian Conference on Computer Vision (ACCV), Jeju Island, Korea, 2004.

4. Rong Xiao, Long Zhu, and Hongjiang Zhang. Boosting Chain Learning for Object Detection , in Proc. of International Conference on Computer Vision (ICCV), Nice, France, 2003.

5. Stan.Z. Li, Long Zhu, Zhengqiu Zhang, Andrew Blake, Hongjiang Zhang, Harry Shum, Statistical Learning of Multi-View Face Detection , In Proceedings of The 7th European Conference on Computer Vision (ECCV), Copenhagen, Denmark, May, 2002.

WEBSITES: www.lacereg.com www.imagestechnology.com www.ieee.com

DEPT.OF ECE

Page 20