In many instances, humans accomplish recognition by a Gestalt comparison of the feature with a catalog, either in hand or in memory. Some recognition tasks require an extensive catalog and organization, as represented by the typical field guides for identifying birds, plants, and so on. The horizontal axis of each plot is the magnitude of the differences in the parameters for each airplane shape. One thing that cross-correlation is quite good at is finding a feature in a cluttered or camouflaged scene. In some situations, such as searching reconnaissance images for objects of military interest, the cross-correlation is performed with target images oriented at angles in steps of about 15 to 20 degrees. When shape is used for classification, choosing the appropriate shape parameters may be done by humans based on prior knowledge and experience, or mathematically by techniques such as principal components analysis …

This paper represents an attempt to use two dimensional image processing and pattern recognition methodologies to identify sound waveforms. The identification process is then used to evaluate the success of the dynamic blind signal separation algorithm.

Zernike moments have been used as shape descriptors in several object recognition applications. The classical method of computing Zernike moments is dependent on the regular moments which makes them computationally expensive and inefficient. In this paper, we present an efficient and fast algorithm for the direct computation of Zernike moments. This algorithm is based on using some properties of Zernike polynomials.

This paper presents two new approaches for optimum thresholding of gray-level images. The first algorithm utilizes an iterative thresholding scheme in conjunction with a golden-section optimization technique to determine the optimum threshold that maximizes the number of contours and the number of pixels in the contours. The second algorithm uses the same optimization technique to determine the optimum threshold that maximizes the average perimeter of the scene image.

An efficient method is described to compute the K-nearest neighbour rule (KNNR). The number of distance computations is reduced considerably without any increase in the error rate. Unlike the other techniques, no preprocessing and approximation are involved in this technique which makes it suitable for overlapped classes.

Moment invariants have been proposed as pattern sensitive features in classification and recognition applications. In this paper, the authors present a comprehensive study of the effectiveness of different moment invariants in pattern recognition applications by considering two sets of data: handwritten numerals and aircrafts.The authors also present a detailed study of Zernike and pseudo Zernike moment invariants including a new procedure for deriving the moment invariants. In addition, the authors introduce a new normalization scheme that reduces the large dynamic range of these invariants as well as implicit redundancies in these invariants.Based on a comprehensive study with both handwritten numerals and aircraft data, the authors show that the new method of deriving Zernike moment invariants along with the new normalization scheme yield the best overall performance even when the data are degraded by additive noise.