Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.

biometric technology

Technology that identifies you based on your physical or behavioral traits- for added security to confirm that you are who you claim to be.(this ppt is very dear to me as i have given a talk on this topic twice. this also fetched me and migmar first prize at deen dayal upadhyay college- converging vectors - an inter college presentation competition organized by arya bhata science forum)

  • Als Erste(r) kommentieren

biometric technology

  1. 1. Anmol Bagga Migmar Dolma BSc. Hons Electronics III Acharya Narendra Dev College, University of Delhi Govindpuri, Kalkaji, New Delhi, India
  2. 2. Contents Of The Presentation <ul><li>What is BIOMETRICS ? </li></ul><ul><li>Its Working </li></ul><ul><li>Contribution In Various Fields </li></ul><ul><li>Comparison Of Biometric Techniques </li></ul><ul><li>Success Rate Of The Applications </li></ul><ul><li>Future Of Biometric Techniques </li></ul><ul><li>Bibliography </li></ul>
  3. 3. Biometrics Technology that identifies you based on your physical or behavioral traits- for added security to confirm that you are who you claim to be.
  4. 4. Introduction <ul><li>Challenges in computing environments </li></ul><ul><ul><li>Computing devices are numerous and ubiquitous </li></ul></ul><ul><ul><li>Traditional authentication including login schemes aren’t reliable any more </li></ul></ul><ul><li>Proposed Solutions </li></ul><ul><ul><li>Use biometrics for authentication </li></ul></ul><ul><ul><li>At the same time, ensure security of biometric templates in an open environment </li></ul></ul><ul><li>Benefits </li></ul><ul><ul><li>Cannot be misused as it authenticates on the basis of who you are but not what you carry (like the password, smartcard or be some keys ) and hence more reliable. </li></ul></ul>
  5. 5. A Biometric system uses the three components: 1. Sensor It detects the characteristic being used for identification 2. Computer It reads and stores the information 3. Software It analyzes the characteristic, translates it into a graph or code and performs the actual comparisons
  7. 7. How Biometrics Works? <ul><li>Enrollment </li></ul><ul><li>The data to be verified is recorded and scanning is done. </li></ul><ul><li>Representation </li></ul><ul><li>The recorded data is converted into a digital representation and stored as a numerical template. </li></ul><ul><li>Matching </li></ul><ul><li>The questioned data is compared to the stored numerical template. </li></ul><ul><li>Verification /Identification </li></ul><ul><li>In verification, an image is matched to only one image in the database (1:1). For example, an image taken may be matched to an image in the database to verify. </li></ul><ul><li>In identification, the image is compared to all images in the database (1:N). For example, the image taken is compared to a database of mug shots to identify who the subject is. </li></ul>
  8. 8. Contributions of Biometrics <ul><li>Finger Print and Hand Geometry Recognition </li></ul><ul><li>Voice Recognition </li></ul><ul><li>Handwriting Recognition </li></ul><ul><li>Iris Scanning </li></ul><ul><li>Vein Geometry Recognition </li></ul><ul><li>Facial Geometry Recognition </li></ul>
  9. 10. Finger Print And Hand Geometry Recognition <ul><li>When the hand is aligned on the scanning screen and applied to the sensor window of the reader, the hand is scanned and a gray-scale image is captured. </li></ul><ul><li>A special computer software then identifies the key minutiae points from the image. </li></ul><ul><li>The points are then converted into a digital representation, called “the numerical template “. </li></ul><ul><li>The numerical template is then compared with the questioned sample and if the match is found, the person’s authentication is proved. </li></ul>
  10. 11. Iris Scanning <ul><li>Iris scanning can seem very futuristic but it uses a simple Digital CCD camera </li></ul><ul><li>It uses both visible and near infrared light to take a clear, high-contrast picture of the iris. </li></ul><ul><li>In the scanner, the camera focuses to make sure that the position is correct and the eye is kept 3 to 10 inches from the camera. </li></ul><ul><li>When the camera takes a picture, the computer locates: </li></ul><ul><li>The center and edge of the pupil. </li></ul><ul><li>The edge of the iris </li></ul><ul><li>The eyelids and eyelashes </li></ul>An iris scanner
  11. 13. <ul><li>The pattern is then analyzed and translated into a code. </li></ul><ul><li>These are more common in high-security applications because people's eyes are so unique and the chance of overlapping is near to impossible. </li></ul><ul><li>They also allow more than 200 points of reference for comparison, as opposed to 60 or 70 points in fingerprints. </li></ul><ul><li>The iris is a visible but protected structure, and it does not usually change over time, making it ideal for biometric identification. </li></ul>
  12. 14. Voice Recognition <ul><li>It utilizes the fact that everybody has a unique voice because of the unique shape of vocal cavities and movements of the mouth while speaking. </li></ul>Speaker recognition systems use spectrograms to represent human voices.
  13. 15. <ul><li>To enroll in a voiceprint system, either the exact words or phrases is required, or an extended sample of speech for the computer to identify no matter what is said. </li></ul><ul><li>The data used in a voiceprint is a sound spectrogram. It is basically a graph that shows sound's frequency and time on the vertical and horizontal axis respectively. </li></ul><ul><li>Different speech sounds create different shapes within the graph . </li></ul><ul><li>Disadvantage </li></ul><ul><li>It has been disadvantageous as any one can access it by simply recording authorized person’s voice and hence less reliable. This is a fact due to which it has remained less popular than other techniques </li></ul><ul><li>To overcome these disadvantages, technologies have been introduced that detects the artifacts created in recording and playback. </li></ul>
  14. 16. Handwriting Recognition <ul><li>Biometric systems analyze the act of writing by examining the pressure used and the speed and rhythm of writing and not just by observing the way in which the words are formed. </li></ul><ul><li>They also record the sequence in which the letters are formed. </li></ul><ul><li>A handwriting recognition system's sensors include a touch-sensitive writing surface or a pen that contains sensors that detect angle, pressure and direction. </li></ul><ul><li>The software translates the handwriting into a graph and recognizes the small changes in a person's handwriting from day to day and over time. </li></ul>This Tablet PC has a signature verification system
  15. 17. <ul><li>This is a unique feature and extremely difficult to tamper with. </li></ul><ul><li>To use the system, your finger, wrist, palm is simply placed on or near the scanner and a digital picture is taken using near-infrared light. </li></ul><ul><li>The hemoglobin in blood absorbs the light, and the veins appear black in the picture and a reference template based on the shape and location of the vein structure is created by the software. </li></ul>Vein Geometry Recognition Vein scanners use near-infrared light to reveal the veins’ pattern.
  16. 18. Facial Recognition System <ul><li>Facial recognition uses a software known as Facelt that is based on the ability to recognize a face and then measure the various features of the face. </li></ul><ul><li>Every face has numerous, distinguishable landmarks, peaks and valleys that make up facial features. Facelt defines these landmarks as nodal points. Each human face has approximately 80 nodal points </li></ul><ul><li>These nodal points are measured creating a numerical code, called a Face Print , representing the face in the database. </li></ul>FaceIt software measures nodal points on the human face to create a face print and find a match
  17. 19. <ul><li>2D FACIAL RECOGNITION </li></ul><ul><li>For it to be effective and accurate, the image captured needed to be of a face that was looking almost directly at the camera, with little variance of light and expressions from image in the data base. </li></ul><ul><li>Even the smallest changes in light or orientation could reduce the effectiveness of the system, so they couldn't be matched to any face in the database, leading to a high rate of failure. </li></ul><ul><li>Hence, we’ve switched over to 3D Facial recognition. </li></ul><ul><li>Facelt software compares the face print with other images in the database. </li></ul>
  18. 20. 3D Face Recognition <ul><li>A newly-emerging trend in facial recognition software uses a 3D model, which claims to provide more accuracy. </li></ul><ul><li>3D facial recognition uses distinctive features of the face - where rigid tissue and bone is most apparent, such as the curves of the eye socket, nose and chin - for identification. </li></ul><ul><li>Using depth and an axis of measurement that is not affected by lighting, 3D facial recognition can even be used in darkness and has the ability to recognize a subject at different view angles with a potential to recognize up to 90 degrees. </li></ul>The Vision 3D + 2D ICAO camera is used to perform enrollment, verification and identification of 3D and 2D face images.
  19. 22. The 3D software system involves a series of steps to verify the identity of an individual <ul><li>1) Detection Acquiring an image can be accomplished by digitally scanning an existing photograph (2D) or by using a video image to acquire a live picture of a subject (3D). </li></ul><ul><li>2) Alignment Once it detects a face, the system determines the head's position, size and pose. Since the subject has the potential to be recognized up to 90 degrees, while with 2D, the head must be turned at least 35 degrees toward the camera . </li></ul><ul><li>3) Measurement The system then measures the curves of the face on a sub-millimeter scale and creates a template . </li></ul>
  20. 23. <ul><li>4) Representation The system translates the template into a unique code. This coding gives each template a set of numbers to represent the features on a subject’s face </li></ul><ul><li>5) Matching </li></ul><ul><li>For a 3D image, different points are identified and measured. (For example, the outside of the eye , the inside of the eye and the tip of the nose ).After these measurements, an algorithm will be applied to the image to convert it to a 2D image. After conversion, the software will then compare the image with the 2D images in the database to find a potential match. </li></ul><ul><li>6) Verification or Identification In verification, an image is matched to only one image in the database (1:1). If identification is the goal, then the image is compared to all images in the database resulting in a score for each potential match (1:N). </li></ul>
  21. 24. Comparison of various biometric technologies <ul><li>It is possible to understand if a human characteristic can be used for biometrics in terms of the following parameters: </li></ul><ul><li>Universality </li></ul><ul><ul><li>each person should have the characteristic </li></ul></ul><ul><li>Uniqueness </li></ul><ul><ul><li>is how well the biometric separates individually from another. </li></ul></ul><ul><li>Permanence </li></ul><ul><ul><li>measures how well a biometric resists aging. </li></ul></ul><ul><li>Performance </li></ul><ul><ul><li>accuracy, speed, and robustness of technology used. </li></ul></ul>
  22. 25. Comparison of various Biometric Technologies ( H =High, M = Medium, L = Low)
  23. 26. How Successful Are These Biometric Techniques
  24. 28. The Future of Biometrics <ul><li>New methods that use DNA, nail bed structure, teeth, ear shapes, body odor, skin patterns and blood pulses </li></ul><ul><li>More accurate home-use systems </li></ul><ul><li>Opt-in club memberships, frequent buyer programs and rapid checkout systems with biometric security </li></ul>A creator of facial recognition software, is currently marketing a system that will keep track of employees' time and attendance. Their Web site states that it will prohibit &quot;buddy punching,&quot; which will cut down on security risks and decreased productivity.
  25. 29. <ul><li>Biometric Time Clocks or Biometric time and attendance systems, which are being increasingly used in various organizations to control employee timekeeping. </li></ul><ul><li>Biometric safes and biometric locks, provides security to the homeowners. </li></ul><ul><li>Biometric access control systems, providing strong security at entrances. </li></ul><ul><li>Biometric systems are also developed for securing access to pc's and providing single logon facilities. </li></ul><ul><li>Applications of biometrics technology in identifying DNA patterns for identifying criminals, etc. </li></ul><ul><li>Biometrics airport security devices are also deployed at some of the world's famous airports to enhance the security standards. </li></ul><ul><li>More prevalent biometric systems in place of passports at border crossings and airports </li></ul>
  26. 31. Bibliography <ul><li>www.google.com </li></ul><ul><li>www.howstuffsworks.com </li></ul><ul><li>e library of NUS </li></ul><ul><li>Biometric Consortium, biometrics.org </li></ul><ul><li>www.cnn.com </li></ul>
  27. 32. Questions?
  28. 33. Thank You