LEARNING-BASED METHOD TO RECOGNIZE AND LOCALIZE GLASSWARE USING LASERRANGE IMAGES

A system that can be trained to recognize and localize glassware locat ed on a workbench using laser range images is described. The training data consists of laser range images of objects of known classification . The image is preprocessed to isolate a box of pixels corresponding t o the object, and then the box is given as an input to a neural networ k. The range readings from the laser range system deviate significantl y from the actual distances to the glassware, and consequently a surfa ce fit to the readings has very little resemblance to the actual glass ware surface. Thus, the straightfoward method of fitting a surface to the images and matching it with the surface of known glassware is not feasible. A first version of the system has been developed based on a system of perceptrons, and the tests have been successful on the image s taken by a PERCEPTRON P5000 laser range finder.