An important problem in pattern analysis is the automatic recognition of an object in scene regardless of the position, size and orientation. In this paper an Invariant Feature Extractor based on the combination of the Radon transform, the Correlation and the fast translation invariant N transform (NT) is described. This Invariant Feature Extractor was used in Invariant Object Recognition System, implemented as a programme package on a powerful PC and tested in recognition experiments on three different classes of objects. The proposed Invariant Object Recognition System has three sub-systems : Digital Image Preprocessing Svstem, Invariant Feature Extractor and Classificator. As Classificator a neural network from the class of ARTMAP neural networks was used.
The aim of this study was to acquire data on the physical properties and compression loading behaviour of seed of six corn hybrid varieties. The mean values of length, width, thickness, geometric diameter, surface area, porosity, single kernel mass, sphericity, bulk and true density, 1 000 kernelmass and coefficient of friction were studied at single level of corn seed moisture content. The calculated secant modulus of elasticity during compressive loading for dent corn was 0.995 times that of the semi-flint type; there were no significant differences in the value of this mechanical property between semi-flint and dent corn varieties. The linear model showed a decreasing tendency of secant modulus of elasticity for all hybrids as the moisture content of seeds increased.