The paper analyses disadvantages of standard feature generation and their standardization for image recognition by Pulse Coupled Neural Network (PCNN). The aim of research was to propose a new form of feature value calculation that improves significantly the quality of generated features. It is part of algorithm for feature generation by optimized PCNN.

No abstract

The paper introduces an approach for threshold potential optimization in the Pulse Coupled Neural Network (PCNN) to solve the quality of generated features for image recognition tasks. Threshold potential plays very important role because it provides and controls pulse effect of PCNN. The suitable control of pulse effect can improve dimension reduction of image classification space by PCNN that is necessary for successful image recognition with high input image dimension.

No abstract