<title>Grayscale image preprocessing for viewpoint-independent 3D extraction of objects</title>

Abstract

ABSTRACT The process by which images are prepared for complex vision systems is nontrivial. In this paper we describe the sequence of steps required to preprocess a grayscale picture for input to the Viewpoint Independent 3-D Extraction and Recognition of Objects (VJTREO) system. VITREO is capable of accepting grayscale pictures for processing into line drawings for input to object recognition subsystems. These drawings are analyzed for edge and surface features to allow the extraction of component parts for subsequentrecognition of the object containing them from stored component descriptions. This analysis demands that theline drawing extraction be robust and a combination of edge and line algorithms are employed. This processis described and examples of VITREO object extraction are shown.Keywords: object recognition, computer vision, edge extraction, edge linking, VITREO 1. INTRODUCTION The Viewpoint Independent 3-D Extraction of Objects system, or V1TREO, was developed[1] to recognize complex objects from grayscale images. The approach used is that described by Biederman asRecognition by Components (RBC) theory, which is described in a number of references [2,3,4]. Simplyput, RBC theory examines a complex object as a combination of what Biederman calls Geometric Icons, orgeons. Thirty-six geons have been specified as various extrusions of shapes across their central axis. This isbest described by the example given in Figure 1.Consider a circle extruded across a straight line, Figure la. This yields a cylinder. Now, reproduce theextrusion process, but this time collapse the circle as the extrusion along the axis progresses, Figure lb. Thisgives us a cone. Finally, if the axis curves during the extrusion, we can create a horn as shown in Figure lc.If the shape, i.e., the circle, is changed to a rectangle, then we get the figures shown in ld.(a)