DOC PREVIEW
UW-Madison ECE 533 - SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATION

This preview shows page 1-2 out of 7 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 7 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 7 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 7 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATIONJosh Easton, Tin-Yau LoINTRODUCTIONThe topic of face recognition for video and complex real-world environments hasgarnered tremendous attention from governments for crime fighting as well as airportterrorism deterrence. However, there has been little attention towards consumer use offace recognition products. The aim of this project is to come up with a simpleimplementation for computer authentication to replace the popular pass-phrase basedauthentication on personal computers. The popularity of high-resolution cameras onmarket made the possibility of face recognition based computer authentication possible.Humans can recognize face even when the matching image is distorted, such as aperson wearing glasses, and humans can perform the task fairly easy. Understanding howhumans decipher and do matching is an important research topic for medical and neuralscientists.APPROACHFacial recognition is an easy task for a human to perform; it is nearly automatic,and requires little mental effort. A computer, on the other hand, has no innate ability torecognize a face, and must be programmed with an algorithm to do so. Even the bestalgorithms available today are not even close to perfect, and rely a lot on statisticallyprobability.There are a few algorithms that can be used, one of which is the Eigenfacesalgorithm. It first must be trained by being given several images of the same face. Theseimages are used to train the computer to recognize several features of a person’s face.Since the face will not be in the exact same pose every time, the face in the picture mustbe centered and scaled. Generally the person’s eyes are used to center the images. Afterthis minor preprocessing, over a hundred signatures are taken of the face. In order to get agood set of signatures, the face needs to be completely exposed, without any form ofobstruction.After the computer has been trained to recognize a certain face, it can then look atany picture of a face, calculate a set of signatures on it, and compare it to every face it hasbeen trained to recognize. It then will compute a set of probabilities for each trained face,and whichever is the most probable will be considered a match. If none of the facesappear to be very probable, then no match will be returned. The Hidden Markov Models method works in much the same way. A set ofsignatures are taken of a face to train it, and are used to compare to a target face to find amatch.WORK PERFORMEDThe first step in our project consisted of researching the various facial-recognitionalgorithms, and determining which would be the most fit for our application. There aremany open source libraries and applications available, each with a different level of ease-of-use and completeness. Intel OpenCV and CSU Face Recognition engine are veryfeatured-rich but they are overly bloated. We decide to use Eigenface engine by KonradDarnok. As the engine itself was written in Java, we used Java to implement the videograbbing and the rest of the front-end. The result is a program that can be used inconjunction with a video camera. The capture program is shown at figure #1.The “FaceRecognitionCap” program in figure #1 is written in Java which utilizesQuicktime Java library sequence grabber library, running on Mac OS X and Windows(with Quicktime installed) to take Snapshot into gray scale image. Therefore we simulatethe authentication by taken a series of trained image using the firewire camera and in ourQuickTime™ and aTIFF (LZW) decompressorare needed to see this picture.figure #1case, the Apple iSight to capture a 320x240 image from sequence grabber (usingQuicktime Java) and convert it into grayscale (with java.awt framework) and finally saveit into JPEG format using Sun’s JIMI image library.Then the “FaceRecognition” Java program is to run the resultant test image against a trained library. The result is printed out in a text window. In a real system, this would be passed to a program that wanted to authenticate a user, such as a screen saver orlogin screen.QuickTime™ and aTIFF (LZW) decompressorare needed to see this picture.figure #2RESULTSThe resulting program we created seemed to function as one would expect bymatching the test image to the closest image. It is good enough for a user to use to loginto their computer. However, it took considerably a while to be able to come up a matchingas the algorithm has to enumerate the trained images. DISCUSSIONUsing facial recognition for a simple task such as computer authentication is veryideal. Computer users often have several passwords to remember, and using such softwarecan eliminate the need to remember them.Facial recognition software is currently used mostly for surveillance. However,computer authentication could potentially be a better use of such software. One reasonwhy is because for normal consumer use, the occasional false negative can be dealt with.However, when doing surveillance, false negatives and false positives are a huge problem.All computer facial recognition algorithms in use today have trouble dealing withobstructions on a person’s face, such as sunglasses. These obstructions can cause falsenegatives. For a home or small office user, a false negative is ok, since the solution is tosimply remove the obstruction from the person’s face and to retry.Also all computer facial-recognition systems which take images from camera canbe easily fooled. A simple method is to put a picture of the person in front of the videocamera, and then requesting authentication. This will trick the program into thinking thereal user is there and grant access. This method should therefore not be used for systemsthat require high security. Instead it is only sufficient to protect unimportant data, such asfor someone’s personal email.However, when using facial recognition on a large scale, such as for surveillance,false negatives are very bad. Since simply wearing sunglasses can defeat the software,then the criminal/bad guys can walk around undetected by wearing sunglasses. There isnot an easy solution for this problem. For the home user, you can simply ask them toremove the obstruction and retry. However, on a large scale, you cannot make sunglassesillegal, and so the problem cannot be worked around.One more


View Full Document

UW-Madison ECE 533 - SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATION

Documents in this Course
Load more
Download SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATION
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATION and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view SIMPLE FACE RECOGNITION IMPLEMENTATION FOR COMPUTER AUTHENTICATION 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?