Effect of different combinations of size and shape parameters in the percentage error of classification of structural elements in vegetal tissue of the pumpkin Cucurbita pepo L. using probabilistic neural networks

Abstract

Abstract

It was proceeded to determine the optimal combination of size and shape parameters in order to obtain the classification of structural elements with the lowest percentage of error. To this effect it was proceeded to use logical sequences and a series of micrographs of tissue pumpkin (Cucurbita pepo L.) from which it was identified and manually classify structural elements in three different classes (cell, intercellular spaces and unrecognizable elements). From each element , eight parameters of size and shape (area, equivalent diameter, major axis length, minor axis length, perimeter, roundness, elongation, compaction) were determined, a logical sequence was developed to determine the combination of parameters that generated the lowest error in the classification of the microstructural elements by comparison with manual classification and determined through this process that the minimum error rate was 12.7%, using the parameters of major axis, minor axis, perimeter and roundness