A method and system for optically recognizing an object from a reference library of known products based on a spectrum of local radius of curvature of the object. A surface portion of an object is illuminated with a pattern of light that permits the extraction of three dimensional coordinates for a set of points on the surface portion of the object. An image data set of the surface portion of the object is then captured with a capture device that is positioned at an angular offset with respect to a source of the light. That is, the combination of the light pattern and the imaging device together generate a two dimensional captured image, from which it is possible to extract the three dimensional coordinates for the set of points on the surface portion of the object. A set of local radii of curvatures are then determined for selected data points in the image data set. A spectrum representing a distribution of the curvatures is then computed for the set of local radii of curvatures. If the data set is for the generation of a library of spectra, it is processed with a dimension reduction analysis to determine a single set of basis functions representing all of the objects and a corresponding set of basis coefficients for each different type of object. If the data set is for an unknown object, then the dimension reduction analysis and the basis functions are applied to the data set to generate an unidentified set of basis coefficients. This latter set is then statistically compared with the reference library of spectra to identify the product or at least designate the closest known products.