Kenneth J. Breeding

Aircraft Identification by Moment Invariants

Although many systems for optical reading of printed matter have been developed and are now in wide use, comparatively little success has been achieved in the automatic interpretation of optical images of three-dimensional scenes. This paper is addressed to the latter problem and is specifically concerned with automatic recognition of aircraft types from optical images. An experimental system is described in which certain features called moment invariants are extracted from binary television images and are then used for automatic classification. This experimental system has exhibited a significantly lower error rate than human observers in a limited laboratory test involving 132 images of six aircraft types. Preliminary indications are that this performance can be extended to a wider class of objects and that identification can be accomplished in one second or less with a small computer.

The Automatic Recognition of Human Faces from Profile Silhouettes

A pattern recognition system is described which is capable of identifying human faces from their full profile silhouettes. Each silhouette is preprocessed to remove noise, smooth edges, and extract the front edge. The processed silhouettes are then represented by a 12-dimensional feature vector, the components of which are obtained by a circular autocorrelation function. Using a weighted k-nearest neighbor decision rule it is shown that a recognition accuracy of 90 percent is attainable in a ten-class problem. An adaptive training procedure is also described which is used for setting up the authority files. This training procedure appears to identify those feature vectors representing a class which are either most important, from an information content point of view, or are observed most often. Finally, a comparison is made between the recognition accuracy obtained using circular autocorrelation features and moment invariant features. It is shown that the former outperforms, in this problem, the latter. The system is also compared to human observers with the result that the system performs no worse than the human observers.

Some Characteristics of Universal Cell Nets

In this paper, one-output n-input combinatorial nondegenerate networks of cells are analyzed. The networks consist of one-output two-input cells that are universal in that they realize all 16 functions of the two-input variables. Such networks have a number of interesting properties, among which is the fact that if network N realizes F(x), it also realizes the dual function Fd(x).

A pattern description language—PADEL

Abstract This paper describes an artificial language, called PADEL, which may be used to describe line drawings. The descriptions consist of strings of concatenated symbols denoting vertices and branches of the picture or line drawing. These picture elements are formally defined followed by a description of the grammar which generates the language. The actual construction of the descriptive strings from a given picture is then discussed. The language is then analyzed and noted to be phrase structured, finite, context free language. The regular expression which describes all strings in the language is then derived. Using the language just described, a set of topological manipulations of the picture are defined by operations on the descriptive strings. Manipulations such as rotations, reflections and scaling are defined on two dimensional picture descriptions. A nonuniform scale change, which may be termed “rubber sheet warping,” is also described. The pattern description language is next extended to the description of three dimensional objects by representing the branch labels as three tuples which are the direction angles of the branch unit vectors. Rotations of such pictures about the coordinate axis are then described. It is then shown that the angular relationships among the branches of the picture remain invariant under these transformations and, thus, the “shape” of the object remains invariant. An inverse rotation is next introduced. Finally projections of the picture onto the principal planes and more generally onto an arbitrary plane is described.

Some Properties of Minimal Threshold Approximations

In recent years, considerable interest has been given to the study of threshold logic. This interest stems primarily from the possible economic savings associated with the use of threshold elements in realizing arbitrary switching functions. Such realizations, for the most part, depend on successfully finding threshold functions that closely approximate the given function. Closeness of approximation as defined here means that the approximating threshold function has the smallest set of error vectors with respect to the given function.

BCD and Radi x-2 Conversions

An algorithm for the conversion of BCD numbers to numbers in the -2 radix system is presented. This algorithm consists of simple arithmetic operations such as division by two and addition of the constants one and five. These operations may easily be performed in a -2 radix computer by shifting a number right for division by two and a table look-up procedure for the additions. The reverse conversion is also briefly discussed