Interactive Face Recognition IFR Nishanth Vincent Fairfield University

Interactive Face Recognition (IFR) Nishanth Vincent Fairfield University Advisor: Professor Douglas A. Lyon, Ph. D.

Interactive Face Recognition n n The Interactive face recognition system is a stand-alone GUI implementation on the Sharp Zaurus SL-6000 L The Zaurus is provided with a 400 MHz processor, 64 MB RAM, and Compact Flash and Serial Device ports It is equipped with a Sharp CE-AG 06 camera attachment which is inserted into the Compact Flash port & a wireless network card The operating system is Embedded Linux with Personal Java support.

Sharp Zaurus – PDA

Camera n The source code for the camera is in C, so we call the executable at runtime using java. private void camera() { try { Runtime. get. Runtime (). exec ("/home/Qt. Palmtop/bin/. /sq_camera"); } catch (IOException ioe) { ioe. print. Stack. Trace (); } }

Problem Definition n We are given an input scene and a suspect database n Goal is to find a set of possible candidates n Challenge is to run the algorithm on the given embedded hardware.

Skin detection – YCb. Cr Color Model Skin detection was performed in the YCb. Cr color model n In this color model, the luminance component is separated from the color components n

GUI for Zaurus

Threshold in YCb. Cr n if ( (Cb[x][y] < 173) && (Cb[x][y] > 133) && (Cr[x][y] < 127) && (Cr[x][y] > 77) ) set. Pixel(x, y, 255); else set. Pixel(x, y, 0); }

Skin Detected Image

Morphological operator : -Dilation n Dilation is defined as a morphological operator, which is usually applied to binary images. The basic effect of the operator on a binary image is to gradually enlarge the boundaries of regions of foreground pixels

Dilated Image

Morphological operator : -Erosion n Erosion is defined as a morphological operator which is also applied to binary images. It is used to erode away the boundaries of regions of foreground pixels. Thus the areas of foreground pixels shrink in size, and holes within those areas become larger

Eroded Image

Face detection

Face Database for Face Recognition

PCA-principal component analysis This algorithm treats face recognition as a twodimensional recognition problem, n It takes advantage of the fact that faces are normally upright and thus may be described by a small set of 2 -D characteristics n Face images are projected onto a feature space ('face space') that best encodes the variation among known face images n

Face Recognition

Conclusion we have presented an interactive face recognition algorithm on the embedded device. n Our work is significantly novel compared to the previous work for the fact that we are able to match the faces from the scene in an interactive time and that our algorithm is able to run on the given embedded hardware n