5 steps of Facial Recognition!

As a biometric, facial recognition is a form of computer vision that uses faces
to attempt to identify a person or verify a person’s claimed identity. Regardless
of specific method used, facial recognition is accomplished in a five step process.

1. First, an image of the face is acquired. This acquisition can be accomplished
by digitally scanning an existing photograph or by using an electro-optical
camera to acquire a live picture of a subject. As video is a rapid sequence of
individual still images, it can also be used as a source of facial images.

2. Second, software is employed to detect the location of any faces in the
acquired image. This task is difficult, and often generalized patterns of what
a face “looks like” (two eyes and a mouth set in an oval shape) are employed
to pick out the faces.

3. Once the facial detection software has targeted a face, it can be analyzed. As
noted in slide three, facial recognition analyzes the spatial geometry of
distinguishing features of the face. Different vendors use different methods
to extract the identifying features of a face. Thus, specific details on the
methods are proprietary. The most popular method is called Principle
Components Analysis (PCA), which is commonly referred to as the eigenface
method. PCA has also been combined with neural networks and local feature
analysis in efforts to enhance its performance. Template generation is the
result of the feature extraction process. A template is a reduced set of data
that represents the unique features of an enrollee’s face. It is important to
note that because the systems use spatial geometry of distinguishing facial
features, they do not use hairstyle, facial hair, or other similar factors.

4. The fourth step is to compare the template generated in step three with those
in a database of known faces. In an identification application, this process
yields scores that indicate how closely the generated template matches each
of those in the database. In a verification application, the generated template
is only compared with one template in the database – that of the claimed
identity.

5. The final step is determining whether any scores produced in step four are
high enough to declare a match. The rules governing the declaration of a
match are often configurable by the end user, so that he or she can determine
how the facial recognition system should behave based on security and
operational considerations.

Examples of Biometrics (www.inttelix.com)

www.inttelix.com

Biometric technologies may seem exotic, but their use is becoming increasingly common, and in 2001 MIT Technology Review named biometrics as one of the “top ten emerging technologies that will change the world.” While this briefing focuses on facial recognition, there are many different types of biometrics as Leonardo DaVinci’s Vitruvian Man makes clear. Examples include:
 


Iris Scan
Iris scanning measures the iris pattern in the colored part of the eye, although the iris color has nothing to do with the biometric. Iris patterns are formed randomly. As a result, the iris patterns in a person’s left and right eyes are different, and so are the iris patterns of identical twins. Iris scanning can be used quickly for both identification and verification applications because the iris is highly distinctive and robust.

Retinal Scan
Retinal scans measure the blood vessel patterns in the back of the eye. The device involves a light source shined into the eye of a user who must be standing very still within inches of the device. Because users perceive the technology to be somewhat intrusive, retinal scanning has not gained popularity;
currently retinal scanning devices are not commercially available.

Facial Recognition
Facial recognition records the spatial geometry of distinguishing features of the face. Different vendors use different methods of facial recognition, however, all focus on measures of key features of the face. Because a person’s face can be captured by a camera from some distance away, facial recognition has a clandestine or covert capability (i.e. the subject does not necessarily know he has been observed). For this reason, facial recognition has been used in projects to identify card counters or other undesirables in casinos, shoplifters in
stores, criminals and terrorists in urban areas.

Speaker / Voice Recognition
Voice or speaker recognition uses vocal characteristics to identify individuals using a pass-phrase. A telephone or microphone can serve as a sensor, which makes it a relatively cheap and easily deployable technology. However, voice recognition can be affected by environmental factors such as background noise. This technology has been the focus of considerable efforts on the part of the telecommunications industry and the U.S. government’s intelligence community, which continue to work on improving reliability.

Fingerprint
The fingerprint biometric is an automated digital version of the old inkand-paper method used for more than a century for identification, primarily by law enforcement agencies. The biometric device involves users placing their finger on a platen for the print to be electronically read. The minutiae are then extracted by the vendor’s algorithm, which also makes a fingerprint pattern analysis. Fingerprint biometrics currently have three main application arenas: large-scale Automated Finger Imaging Systems (AFIS) generally used for law enforcement purposes, fraud prevention in entitlement programs, and physical and computer access.

Hand/Finger Geometry
Hand or finger geometry is an automated measurement of many dimensions of the hand and fingers. Neither of these methods takes actual prints of the palm or fingers. Spatial geometry is examined as the user puts his hand on the sensor’s surface and uses guiding poles between the fingers to properly place the hand and initiate the reading. Finger geometry usually measures two or three fingers. Hand geometry is a well-developed technology that has been thoroughly field-tested and is easily accepted by users. Because hand and finger
geometry have a low degree of distinctiveness, the technology is not well-suited for identification applications.

Dynamic Signature Verification
We have long used a written signature as a means to acknowledge our identity. Dynamic signature verification is an automated method of measuring an individual’s signature. This technology examines such dynamics as speed, direction, and pressure of writing; the time that the stylus is in and out of contact with the “paper,” the total time taken to make the signature; and where the stylus is raised from and lowered onto the “paper.”

Keystroke Dynamics
Keystroke dynamics is an automated method of examining an individual’s keystrokes on a keyboard. This technology examines such dynamics as speed and pressure, the total time taken to type particular words, and the time elapsed between hitting certain keys. This technology’s algorithms are still being developed to improve robustness and distinctiveness. One potentially useful application that may emerge is computer access, where this biometric could be used to verify the computer user’s identity continuously.

Advantages of Face Recognition (In Surveillance)

Advantages of Facial Recognition in Surveillance

The concept of recognizing someone from facial features is intuitive, facial recognition, as a biometric, makes human recognition a more automated, computerized process. What sets apart facial recognition from other biometrics is that it can be used for surveillance purposes. For example, public safety authorities want to locate certain individuals such as wanted criminals, suspected terrorists, and missing children. Facial recognition may have the potential to help the authorities with this mission. Facial recognition offers several advantages.

The system captures faces of people in public areas, which minimizes legal concerns for reasons explained below. Moreover, since faces can be captured from some distance away, facial recognition can be done without any physical contact. This feature also gives facial recognition a clandestine or covert capability.

For any biometric system to operate, it must have records in its database against which it can search for matches. Facial recognition is able to leverage existing databases in many cases. For example, there are high quality mugshots of criminals readily available to law enforcement. Similarly, facial recognition is often able to leverage existing surveillance systems such as surveillance cameras or closed circuit television (CCTV).

To know more visit : www.inttelix.com

Face Recognition SDK

The FACEPORT.OCX ACTIVEX allows fast use, development and implementation of facial recognition capabilities in existing or newly designed applications. The component provides an easy to use Methods, Properties and Events that simplify the facial recognition development process.

The FACEPORT ActiveX was specially designed for embedded environments like Intel ATOM CPU, and runs very well on Low performance CPU as well as high performance CPUs. The component supports Web Cameras, IP or Analog cameras through external an injection mechanism. The component includes internal web camera management. The component contains an internal Database that provides fast yet reliable management of the matching subjects.

FACEPORT SDK

The FACEPORT FRS SDK allows third-party developers to implement our advanced facial biometric technology within their own security applications. The SDK provides tracking, enrollment, verification, classification, database, communication, and multimedia controls.

Applications

Security

• Access Control
• Suspect Detection
• Time Attendance
• Web Login
• PC Login

Commercial

• Repeated clients
• Interactive Content
• Customer counting
• Graphical Applications

Licensing

• PC based

SCREEN SHOT OF ACTIVEX RUNNING

Face Recognition Database

• Jet 4.0 - MS Access database (Optional: ODBC)
• Log Database : Jet 4.0 MS Access database
• Provides all interfaces necessary to Add, Delete and Retrieve biometric templates, images and users from the central database.

Properties

Name of Property	Description
NoOfFramesForValidation	Min. number of frames for validation
NoOfFramesForEnrollment	Min. number of frames for enrollment
FaceConfidenceThreshold
MinimalIOD	Min. Inner distance between 2 eyes (Default 60)
MaximalIOD	Max. Inner distance between 2 eyes (Default 1500)
FaceQualityThreshold
MatchingThreshold	Min. value for matching
FAR	Will be calculated from matching threshold (theoretical value)
MatchingAttempts	number of matching attempts
AllowLiveness	Boolean - will define if we need to use liveness test
LivenessThreshold	how strict to check for Liveness in an image.(default 50)
MaxRecordsPerTemplate
AllowAging	Boolean - will define if we need to use aging+
AgingMinimalThreshold
EnrolledFaceImagePath
RejectedFaceImagePath
ValidatedFaceImagePath
LogDBPath
FRSDBPath
IsRegistered	returns true if registered
FRR	Will be calculated from matching threshold (theoretical value)
Camera	Gets/Sets the currently selected Camera
VideoFormat	Gets/Sets the Currently Selected Camera’s Video Format.
FlipImagesHorizontal	Gets/Sets value whether to Flip the Images Horizontally
SaveEnrolledFaceImage	Gets/Sets value Whether to Save the Learned/Enrlolled Face Image to harddisk
SaveRejectedFaceImage	Gets/Sets value Whether to Save the Rejected Face Image to harddisk
SaveValidatedFaceImage	Gets/Sets value Whether to Save the Validated/Matched Face Image to harddisk

Events

Name of Events	Description
CameraOpened()
CameraClosed()
NewCameraFrame(bitmap image)	for every new frame
ExceptionHappened(string Description, int ErrorNumber)
FaceLearnt(int FaceQuality, float Similarity, float FaceConfidence, int IOD)	after new enrollment
FaceValidated(int FaceQuality, float Similarity, float FaceConfidence, int IOD)	after validation
FaceLearningFailed(int ErrorTypeID, String Description, int FaceQuality, float Similarity, float FaceConfidence, int IOD )	after failure of enrollment
FaceValidationFailed(int ErrorTypeID, String Description, int FaceQuality, float Similarity, float FaceConfidence, int IOD)	after failure of validation
FaceDeleted()	after deletion of face
LogOverflow()	when log record number is above 500K records

Methods

Name of Method	Description
InitializeFRS()
OpenFRSSettingsDialog()	open face recognition component configuration
Bool LearnFaceFromCamera(string FaceID)
Bool LearnFaceFromImage(string FaceID, string ImagePath)
Bool ValidateFace(string FaceId)
Bool OpenCamera(string camera)
String[] GetRejectedImagesByFaceID(string FaceID)
String[] GetRejectedFaceIDsFromDate(string FromDate, string ToDate)
DeleteRejecedImagesFromDate(string FaceID, string UpToDate)
DeleteAllRejecedImagesFromDate(string UpToDate)
String[] GetImagesByFaceID(string FaceID)
DeleteFaceID(string FaceID)
Bool DeleteFaceIDImages(string FaceID, string UpToDate)
Float MatchImageWithFace(string filename, string FaceID)	between the two faces
AddToLog(string timestamp, string type, string data)
ClearLog()	Clear Log db
String[] GetConnectedCameras()
CloseCamera()
ShowCameraPreviewDialog(int x,y)- -1,-1	center of screen
bool SaveSnapshot(string Filename)
PlaceImageAnnotation(string TargetFilename, string Data)
InjectImage(ByVal HImage As Long)	Injects an Image using it HBITMAP or Image
HandleInjectImageFromFile(ByVal fileName As String)	Injects an Image from a File

Face Recognition Time Attendance

Facial Recognition

Time Attendance

Why OnTime Compact ?

• Want to avoid buddy punching, clock padding and general inaccuracy of time capture?
• Fed up with errors in capturing attendance time manually? Or spending time doing the difficult task of consolidating data from various sources?
• Would you prefer to have a system as easy to use as fingerprint with more durability, accuracy and data usability?

• Visual view of video input
• Visual view of face detection
• History / Enrolled / Suspects view
• Voice alerts during system operation
• Easy to use graphic interface
• Fast and accurate face verification

Employee Verification

OnTime Compact is a Time & Attendance System with a Face recognition mechanism, specifically designed to provide irrefutable personal verification. It consists of a standard Camera and OnTime Software to enroll and verify employees, store their Face records, keep logs and interface with computers. OnTime Compact provides enhanced security and superior speed. Employee IN & OUT times are stored as Soft Data. This reduces the manual drudgery of Data Entry, Register maintenance and monthly requirement of Punch Cards for conventional Time Clocks to a minimum.

Software Specifications

• Facial Recognition customizable engine
• Generic video interface (Win 32 API)
• Real time facial detection
• Real time facial matching
• Enhanced matching mechanism (Matching attempts)
• Adjustable image processing
• User Management / Time Zones
• Time Attendance feature (In / Out) (Reasons)
• Fully customizable Time Attendance
• Log Browser including visual history
• User Privacy mode - no image savings

Device

• Device:7" LCD Display
• Internal Video Camera
• Internal Speaker

DEVICE

Employee database maintains information like..

• Face Id
• Full Name
• Job Description
• Supervisor Name
• Validity Period
• Shift Timing (customizable)

SOFTWARE INTERFACE

Facial Recognition Adjustable Attributes

• Minimal Similarity Level
• Eye distance
• Matching attempts
• Face sample rate

Get more details @ www.inttelix.com

Facial Recognition for Network Security

Facial Recognition

Network Security

FRS Supervision is a Cutting-Edge solution for remote facial recognition through Web / 3rd Generation (3G) Cellular and TCP/IP networks. The solution allows both local and remote recognition through fast and smart facial recognition engine. The system performs 24/7 supervision on user activities.
FRS Supervision is a revolutionary technology that facilitates secure log in to the Microsoft Windows Environment. The Software runs an automatic scan, then detects and matches the physical presence of the user, thereby eliminating the need for a username or password.

• Hands Free Login using face detection
• Constant search for the presence of the user
• Automatic lock for unauthorized user
• Unlimited number of users (subject to database size limitations)
• Fast and Accurate face detection
• Works with normal 640 x 480 pixels Web Camera (Interpolation cameras not required)
• Supports LAN, WAN and VPNs
• Manual Login with password
• 1:N matching

Server Side

• View list of connected users
• User information & image acquisition available on request
• User activity history available as log file
• User image can be saved as acquisition data.
• Possible to view users in multi view screen
• The Server software allows to view users in multi view screen
• 4/8/16 users at once (upon configuration).

Client Side

• Allows up to 5 local users per machine
• Software allows user managements.(Enroll/Delete/Username + Password)
• System screen is locked when user is absent for a period of time (Interval)
• The user can manually lock his PC
• The user can select the relevant video source
• The user can configure Video device up to his driver configuration

Supported Cameras

• Full support for Analog Cameras
• IP Cameras
• Full support for USB Camera
• Supports in Logitech®, Microsoft®, Vivotek®, Axis® Cameras 

Visit for more details : www.inttelix.com

FAQs on Facial Biometrics

1.What is biometrics?

Biometrics is the science of measuring and studying biological data. In I.T., biometrics refers to technologies that measure and analyze human body characteristics, such as fingerprints, eye retinas and irises, voice patterns, facial patterns and hand measurements, for authentication purposes.

2.What is the most common biometrics?

Fingerprints have been using successfully in a law enforcement environment for over 100 years. New biometrics systems have emerged in recent years including Hand Geometry, Iris Recognition, Retina Recognition, Signature Verification, Vein Patterns, Facial Recognition and DNA.

3.What is a Facial Recognition System?

Facial Recognition system is a computer program that is used for identifying a person automatically. Research on this technology started in the mid 1960s. The technology works by using several facial features in a person's image and comparing these with existing images in the database. Facial recognition systems are used as an additional and mass security measure and are comparable to the other biometric security systems available today such as retina scanners, fingerprint scanners, etc.

4.How well do biometrics work?

Used in the right environment, biometrics can make a major contribution to improving security. It has to be understood that no single biometric that can be used in real-time is 100% accurate. However when used in conjunction with a personal identifier such as an ID card or PIN, it can be a very effective means for verifying one’s individuality. Its importance generally comes as an aid to recognition rather than guaranteeing someone's identity.

5.How are biometrics selected?

While the emphasis will differ in different applications, the following criteria are used to determine which biometric should be used in a specific application:

• accuracy
• speed
• intrusiveness

6.How does biometrics work?

Almost all biometrics work essentially in the same way. The finger/face/iris is scanned and the locations of key features of the pattern relative to each other are determined. This information is transformed into a digital string and then it is added to the individual's record. When a match is undertaken, the process is repeated and a second string is generated. By matching this string with the one on the individual's record and comparing the result to a user-specified acceptance threshold,the system can establish the facts on the individual’s claim on his identity.

7.What is the Technology behind Facial Recognition Systems?

The most important factor in Facial Recognition systems is its ability to differentiate between the background and the face. This is very important when the system has to identify a face within a crowd. The system then makes use of a person's facial features - its peaks, valleys and landmarks - and treats these as nodes that can be measured and compared against those that are stored in the system database. There are approximately 80 nodes comprising the face print that the system makes use of and this includes the jaw line length, eye socket depth and distance between the eyes, cheekbone shape, and the width of the nose.

8.What is FAR, FRR ?

The accuracy of face recognition system is often defined in terms of two parameters, False Rejection Rate (FRR) and False Acceptance Rate (FAR).
FRR measures how often an authorized user, who should be granted access, is not recognized, while FAR measures how often non-authorized user, who should not be granted access, is falsely recognized.
The control of FRR and FAR through recognition threshold adjustment defines the accuracy of face recognition system. When the recognition threshold is increased, it will adversely cause FAR to decrease. At the same time however, the increase of recognition threshold will result in the increase of FRR. For example, when recognition threshold is set at 100%, FRR rate will increase to its highest level.

9.What is Live Detection?

Live Detection Technology detects and memorizes the background where the camera is facing as part of parameters for identification and verification process. It can effectively detect the difference between a photo and a person in order to prevent imposters to gain access using photos

10.What is Moving Detection?

Face Recognition System is equipped with moving detection function that analyzes the captured image periodically to identify the presence of a moving object and its position. The face detection function then analyzes images to detect a human face and its position.
These two functions can be integrated to provide automated surveillance for detecting moving faces, positioning and data recording. The records can be used in Face Recognition System for enrollment purpose.

11.Three-Dimensional facial Recognition Systems

The new facial recognition systems make use of three-dimensional images and are thus more accurate than their predecessors. Just like two-dimensional facial recognition systems, these systems make use of distinct features in a human face and use them as nodes to create a face print of a person. Unlike two-dimensional face recognition systems, however, they have the ability to recognize a face even when it is turned 90 degrees away from the camera. Moreover, they are not affected by the differences in lighting and facial expressions of the subject.