Essay: Facial recognition

CHAPTER ONE
INTRODUCTION
1.1 Facial Recognition:
This system is a computer application for verifying or identifying a person from a digital image or a video frame from a video source, One of the ways to do this is by comparing selected facial features from the image or a facial database.
Facial recognition is typically used in security systems and can be compared to other biometrics such as fingerprint or eye iris recognition systems.
The face is an important part of who you are and how people identify human. Except in the case of identical twins. The human face is arguably a person’s most unique physical characteristics, while humans being have the innate ability to recognize and distinguish different faces for millions of years, computers are just now catching up.
For face recognition there are two types of comparisons. The first comparison is verification. In verification comparison is where the system compares the given individual with who that individual says they are and gives a yes or no decision. Identification is the second comparison. This is where the system compares the given individual to all the other individuals in the database and gives a ranked list of matches. All authentication or identification authentication technologies operate using the following four stages:
• Capture: a behavioral or physical sample is captured by the system during enrollment and also in identification or verification process.
• Extraction: A unique data is extracted from the sample and a template is created.
• Comparison: the comparison of template has to be done with a new sample.
• Match/non match: the decision has to be made by the system if the features extracted from the new sample are a match or a non match.
Face recognition technology analyze the unique pattern, shape and positioning of the facial features. This is very complex technology and is largely software based. tailored algorithms is used to establishes the analysis framework of this Biometric Methodology for each type of biometric device. This starts with a picture, attempting to find a person in the image. The facial recognition system can be accomplished using several methods including movement, skin tones, or blurred human shapes. This locates the head and finally the eyes of the individual. A matrix is then developed based on the characteristics of the individual’s face. The method of defining the matrix varies according to the algorithm (the mathematical process used by the computer to perform the comparison). The matrix is then compared to matrices that are in a database and a similarity score is generated for each comparison.
The information age is quickly revolutionizing the way transactions are completed. This growth in electronic transactions has resulted in a greater demand for fast and accurate user identification and authentication. Everyday actions are increasingly being handled electronically, instead of face to face or with pencil and paper. Access codes for buildings, banks accounts and computer systems often use PIN’s for identification and security clearances.
Using the proper PIN gains access, but the user of the PIN is not verified. An unauthorized user can often come up with the correct personal codes, When credit and ATM cards are lost or stolen, Despite warning, many people continue to choose easily guessed PIN’s and passwords: social security numbers, and birthdays, phone numbers. Recent cases of identity theft have heighten the need for methods to prove that someone is truly who he/she claims to be.
Face recognition technology may solve this problem since a face is undeniably connected to its owner expect in the case of identical twins. Face is nontransferable. The system can then compare scans to records stored in a central or local database or even on a smart card.
1.1 What are biometrics?
A biometric is a unique, measurable characteristic of a human being that can be used to automatically recognize an individual or verify an individual’s identity. System Biometrics can measure both physiological and behavioral characteristics.
Physiological biometrics (This is based on measurements and data derived from direct measurement of a part of the human body) include:
a. Finger-scan
b. Facial Recognition
c. Iris-scan
d. Retina-scan
e. Hand-scan
Behavioral biometrics (This is based on measurements and data derived from an action) include:
a. Voice-scan
b. Signature-scan
c. Keystroke-scan
Biometric system include the hardware and software used to conduct biometric identification or verification.
1.2 Why Face Recognition?
Among many reasons to choose face recognition includes the following
a. It requires no physical interaction on behalf of the user.
b. It is accurate and allows for high enrolment and verification rates.
c. It does not require an expert to interpret the comparison result.
d. It can use your existing hardware existing cameras, infrastructure and image capture
Devices will work with no problems
e. It is the only biometric that allow you to perform passive identification in a one to.
Many environments
1.3 Face Recognition
The face is arguably a person’s most unique physical characteristics; the face is an important part of who you are and how people identify you. Except in the case of identical twins. While humans have the innate ability to recognize and distinguish different faces for millions of years, computers are just now catching up.
For face recognition there are two types of comparisons, verification is the first comparison. This is where the system compares the given individual with who that individual says they are and gives a positive or negative decision. Identification is the second comparison. This is where the system compares the given individual to all the other individuals in the database and gives a ranked list of matches. All authentication or identification technologies operate using the following four stages:
• Capture: a physical or behavioral sample is captured by the system during enrollment and also in identification or verification process.
• Extraction: unique data is extracted from the sample and a template is created.
• Comparison: the template is then compared with a new sample.
• Match/non match: the system decides if the features extracted from the new sample are a match or a non match.
Face recognition technology analyze the unique pattern, shape and positioning of the facial features. This is very complex technology and is largely software based. tailored algorithms is used to establishes the analysis framework of this Biometric Methodology for each type of biometric device. This starts with a picture, attempting to find a person in the image. The facial recognition system can be accomplished using several methods including movement, skin tones, or blurred human shapes. This locates the head and finally the eyes of the individual. A matrix is then developed based on the characteristics of the individual’s face. The method of defining the matrix varies according to the algorithm (the mathematical process used by the computer to perform the comparison). The matrix is then compared to matrices that are in a database and a similarity score is generated for each comparison.
1.4 -Dimensional Recognition
Three-dimensional or 3D face recognition is a newly emerging trend claimed to achieve improved accuracies. This technique uses 3D sensors to capture information about the shape of a face. The information captured by the sensor is then used to identify distinctive features on the surface of a face, like nose, the contour of the eye sockets and chin.
One advantage of 3D facial recognition is that it can identify a face from a range of viewing angles, including a profile view. It also not affected by changes in lighting like other techniques. 3D data points from a face vastly improve the precision of facial recognition. Three-dimensional research is enhanced by the development of sophisticated sensors that do a better job of capturing 3D face imagery. This sensors work by projecting structured light onto the face, Up to a dozen or more of these image sensors can be placed on the same CMOS chip—each sensor captures a different part of the spectrum.
Even a perfect 3D matching technique could be sensitive to expressions recognition. For that goal a group at the Technion applied tools from metric geometry to treat expressions asisometries A company called Vision Access created a firm solution for 3D facial recognition. The 3D company was later acquired by the biometric access company Bios crypt Inc.which developed a version known as 3D Fast Pass.
Three-dimensional face recognition (3D face recognition) is a modality of facial recognition methods in which the three-dimensional geometry of the human face is used. It has been shown that 3D face recognition methods can achieve significantly higher accuracy than their 2D counterparts, rivaling fingerprint recognition.
3D face recognition has the potential to achieve better accuracy than its 2D counterpart by measuring geometry of rigid features on the face. This avoids such pitfalls of 2D face recognition algorithms as change in lighting, different facial expressions, make-up and head orientation. Another approach is to use the 3D model to improve accuracy of traditional image based recognition by transforming the head into a known view. Additionally, most 3D scanners acquire both a 3D mesh and the corresponding texture. This allows combining the output of pure 3D matchers with the more traditional 2D face recognition algorithms, thus yielding better performance
Face recognition, as a complex pattern recognition problem, has been extensively studied and widely used in many fields over the past decades. Many new methods have been developed and adopted for this issue, and greatly enriched and broadened the pattern recognition field. Recently, researchers have paid much attention on the face recognition, detection, tracking, and also the feature positioning technology. Face recognition is one of the important steps in the human—computer interaction and the purpose is to segment the face region that back ground is not included from the image. Because of irregularities of face shape as well as diversity of lighting and background conditions, the existing algorithms can only be used to handle some specific problems under certain experimental environments, such as the location and status of the human face. However, in practical applications, the direction and angle of rotation and the position of the faces are not fixed in lots of images and video sources, which greatly increase the difficulty of the face recognition. Also, the face direction represents the direction of human attention and the declaration of intent in the human facial expression. Therefore, the estimate on human face direction is critical in face recognition application.
In the field of face recognition, few researchers have been involved in face direction estimation. In previous studies, Hongoetal. [15] applied a linear discriminant analysis to the face direction estimation. Some other researchers improved the method by removing adverse effects of the facial horizontal rotation on the recognition process [3,4,14]. However, the problem of the face direction estimation is much more complex in practice. Therefore, the human face direction estimation and recognition will be a very meaningful and challenging work.
The last few decades have witnessed successful applications of artificial neural networks(ANNs) in various fields including pattern recognition, image processing, fault diagnosis, etc. The study of neural networks has therefore gained persistent research interests from the early1980s, see [4,21,23,27—31] and the references therein. ANNs, as both predictors of dynamic non-linear models and pattern classifiers for evaluation, have been suggested as a possible technique to cope with the face direction recognition. Instead of requiring an accurate mathe-matical model of the process, these approaches only need representative training data. However, owing to some in herent defect sin ANNs, such as existence of local minima and difficulty in choosing the proper size of network, many researchers have proposed wavelet neural networks (WNNs) for the face direction recognition [32]. WNN has widely been applied to the face direction recognition field due to its strong advantages in dealing with non linear mapping capacity to solve complex nonlinear estimating problem. Mean while, WNN inherits the merits from the wavelet analysis in expanding and contracting basis function, which makes it to have stronger self-learning and classification capacity than conventional neural network. WNNs are inspired by the feed-forward neural networks and wavelet decomposition theories. Since such WNNs are based on multi-resolution analysis(MRA) of wavelet transforms, wavelet decompositions provide a useful basis for localized approximation of uncertainty with any degree of regularity at different scales. Incorporating the time-frequency localization properties of wavelets and the learning abilities of ANNs, WNNs have shown their advantages over the regular ANN systems, which can dramatically improve the convergence speed [5,13,16].