Beruflich Dokumente
Kultur Dokumente
Second Presentation
Submitted By: Amit Shah (07-CSS-62) Sheel Sindhu Manohar(07-CSS-62)
Introduction
Describes a face detection framework that is capable of processing images extremely rapidly while achieving high detection rates. Feature Based Detection Image representation using Integral Image which allows the features used by our detector to be computed very quickly. Built using the AdaBoost learning algo-rithm (Freund and Schapire, 1995) to select a small number of critical visual features from a very large set of potential features.
Feature Used
The simple features used are reminiscent of Haarbasis functions which have been used by Papageorgiouet al. (1998). We used three kinds of features. The value of a two-rectangle feature is the difference between the sum of the pixels within two rectangular regions. The regions have the same size and shape and are horizontally or vertically adjacent A three-rectangle feature computes the sum within two outside rectangles subtracted from the sum in a center rectangle. Finally a four-rectangle fea- ture computes the difference between diagonal pairs of rectangles
Haar Feature
Integral Image
Rectangle features can be computed very rapidly using an intermediate representation for the image which we call the integral image. The integral image at location x, y contains the sum of the pixels above and to the left of x, y, inclusive:
Features detection
We choose to generate a very large and varied set of rectangle features. Typically the representation is about 400 times overcomplete. Rectangle features provide a rich image representation which supports effective learning. The extreme computational efficiency of rect-angle features provides ample compensation for their limitations. Like most face detection systems, our de-tector scans the input at many scales; starting at the base scale in which faces are detected at a size of 24 24 pixels, a 384 by 288 pixel image is scanned at 12 scales each a factor of 1.25 larger than the last.
Feature detection(contd.)
The conventional approach is to compute a pyramid of 12 images, each 1.25 times smaller than the previous image. A fixed scale detector is then scanned across each of these images. Computation of the pyramid, while straightforward, requires significant time. Imple-mented efficiently on conventional hardware (using bi-linear interpolation to scale each level of the pyramid) it takes time according to the processor(System dependent).
Wor
Face has been detected succesfully. AdaBoost is an effective pro-cedure for searching out a small number of good fea-tures . We are working on the Training part of the algorithm. Database Used For Training: http://cbcl.mit.edu/softwaredatasets/heisele/download/MIT-CBCL-facerec-database.zip
Future $ddition
Extracting faces detcted in face detection. And storing in a database which would be used for further training of the classifier. Real time Face recognition