Object Detection in the Presence of Clutter Using Gabor Filters

In this paper the problem of detecting objects in the presence of clutter is studied. The images considered are obtained from both visual and infra-red sensors. A feature-based segmentation approach to the object detection problem is pursued, where the features used are computed over multiple spatial ori-entations, and frequencies. The method proceeds as follows: A given image is passed through a bank of even-symmetric Gabor lters. A selection of these ltered images is made and each (selected) ltered image is subjected to a nonlinear (sigmoidal like) transformation. Then, a measure of texture \energy" is computed in a window around each transformed image pixel. The texture \energy" features, and their spatial locations, are inputted to a squared error clustering algorithm. This clustering algorithm yields a segmentation of the original image-it assigns to each pixel in the image a cluster label that identiies the amount of mean local energy the pixel possesses across diierent spatial orientations, and frequencies. This method is applied on a number of visual and infra-red images, each one of which contains one or more objects. The region corresponding to the object is usually segmented correctly, and a unique set of texture \energy" features is typically associated with the segment containing the object(s) of interest.