Hadar I. Avi-Itzhak

Multiple subclass pattern recognition: A maximin correlation approach

This paper addresses a correlation based nearest neighbor pattern recognition problem where each class is given as a collection of subclass templates. The recognition is performed in two stages. In the first stage the class is determined. Templates for this stage are created using the subclass templates. Assignment into subclasses occurs in the second stage. This two stage approach may be used to accelerate template matching. In particular, the second stage may be omitted when only the class needs to be determined. The authors present a method for optimal aggregation of subclass templates into class templates. For each class, the new template is optimal in that it maximizes the worst case (i.e. minimum) correlation with its subclass templates. An algorithm which solves this maximin optimization problem is presented and its correctness is proved. In addition, test results are provided, indicating that the algorithms execution time is polynomial in the number of subclass templates. The authors show tight bounds on the maximin correlation. The bounds are functions only of the number of original subclass templates and the minimum element in their correlation matrix. The algorithm is demonstrated on a multifont optical character recognition problem. >

Straight Line Extraction Using Iterative Total Least Squares Methods

In this paper we present a new algorithm for enhancing the accuracy of the parameter extraction of straight lines in a two-dimensional image. The algorithm achieves high accuracy in comparatively less computational time than most traditional methods and is invariant under rotation and translation. The Iterative Total Least Squares (ITLS) method starts from an initial estimate of the line parameters. When no a priori information about the image is available this estimate can be assigned randomly. Alternately, a lower accuracy method can be used to generate an initial estimate which will result in faster convergence. Then, a rectangular window is centered using the current line approximation, and a new line estimate is generated by making a total least squares fit through the pixels contained within the window. This is repeated until convergence is reached. Adaptively adjusting the window size yields the 4D ITLS process. In addition, a pairwise accelerated ITLS method has been developed which substantially increases the convergence rate. We conclude with some examples where the ITLS method has been used successfully.

Estimation of linear stroke parameters using iterative total least squares methods

In this paper we present an algorithm to enhance the accuracy of the estimation of the parameters of linear stroke segments in a two-dimensional printed character image. The algorithm achieves high accuracy in comparatively less computational time than most traditional methods. It is invariant under rotation and translation and no a priori information about the image is required. The Iterative Total Least Squares (ITLS) method begins at a randomly assigned initial approximation of the line parameters. A rectangular window is centered using the current stroke approximation, and a new line estimate is generated by making a total least squares fit through the pixels contained within the window. This is then repeated until convergence is reached. Adaptive adjustments of the window size and choice of profile can further improve the obtained accuracy. In addition, a `fast ITLS method has been developed.