Gösta H. Granlund

Fourier Preprocessing for Hand Print Character Recognition

A pattern-recognition method, making use of Fourier transformations to extract features which are significant for a pattern, is described. The ordinary Fourier coefficients are difficult to use as input to categorizers because they contain factors dependent upon size and rotation as well as an arbitrary phase angle. From these Fourier coefficients, however, other more useful features can easily be derived. By using these derived property constants, a distinction can be made between genuine shape constants and constants representing size, location, and orientation. The usefulness of the method has been tested with a computer program that was used to classify 175 samples of handprinted letters, e.g., 7 sets of the 25 letters A to Z. In this test, 98 percent were correctly recognized when a simple nonoptimized decision method was used. The last section contains some considerations of the technical realizability of a fast preprocessing system for reading printed text.

Local multiscale frequency and bandwidth estimation

This paper describes a robust algorithm for estimation of local signal frequency and bandwidth. The method is based on combining local estimates of instantaneous frequency over a large number of scales. The filters used are a set of lognormal quadrature wavelets. A novel feature is that an estimate of local frequency bandwidth can be obtained. The bandwidth can be used to produce a measure of certainty for the estimated frequency. The algorithm is applicable to multidimensional data and examples of the performance of the method are demonstrated for one-dimensional and two-dimensional signals.<<ETX>>

An Associative Perception-Action Structure Using a Localized Space Variant Information Representation

Most of the processing in vision today uses spatially invariant operations. This gives efficient and compact computing structures, with the conventional convenient separation between data and operations. This also goes well with conventional Cartesian representation of data.

Image Analysis and Reconstruction using a Wavelet Transform Constructed from a Reducible Representation of the Euclidean Motion Group

Inspired by the early visual system of many mammalians we consider the construction of-and reconstruction from- an orientation score

Estimation of velocity, acceleration and disparity in time sequences

{\it U_f}:\mathbb{R}^2 \times S^{1} \to \mathbb{C}

The application of an oblique-projected Landweber method to a model of supervised learning

as a local orientation representation of an image,

Ectomography A New Radiographic Method for Reproducing a Selected Slice of Varying Thickness

f:\mathbb{R}^2 \to \mathbb{R}