GSLDA- BASED FACE DETECTION

In this paper we presents advanced technique for face detection from image using (GSLDA) i.e. .Greedy Sparse Linear Discriminate Analysis which is efficient for processing images extremely rapidly and achieving high detection rates as compare to AdaBoost [1].We propose to arrange classifiers in parallel, with critical order of grid which rapidly detect faces. The research work for face detection perform in three steps: first is the feature selection method and introduction of a new image representation called the “Integral Image” which allows the features used by our detector to be computed very quickly for each classifier. The second is learning algorithm, based on GSLDA which selects weak classifiers based upon the maximum class separation criterion [2, 3]. The third contribution is to arrange classifiers in a “parallel” which shows face detection faster as compare to cascade. Our results confirm that object detection give high detection rates 94% together with 0.28% false positive rate. It detects 14 frames per second on MIT+CMU dataset. ?