Human shape recognition using radon transform and regularized principal component

The aim of this study is to investigate the potential of Radon Transform and Regularized Principal Component Analysis as feature extraction for classification of human and non human. Several training algorithms are used for the neural network. The finding of the investigation shows that the best training algorithm is Lavenberg-Marquardt (LM). In addition, the execution time taken by LM is fastest among the training.The outcomes of the proposed method using LM are 0% False Rejection Rate (FRR) and 0% False Acceptance Rate (FAR)ona database of 100 images on each category.