Title :
Human shape recognition using radon transform and regularized principal component
Author :
Mahmud, A.R. ; Tahir, Nooritawati Md
Author_Institution :
Fac. of Electr. Eng., Univ. Teknol. MARA, Shah Alam, Malaysia
Abstract :
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.
Keywords :
Radon transforms; feature extraction; image classification; principal component analysis; shape recognition; visual databases; FAR; FRR; Lavenberg-Marquardt algorithm; Radon transform; classification; false acceptance rate; false rejection rate; feature extraction; human shape recognition; image database; regularized principal component analysis; Classification algorithms; Feature extraction; Humans; Principal component analysis; Training; Transforms; Vehicles; Principal Component Analysis; Radon Transform; artificial neural network; classification rate; execution time; training algorithm;
Conference_Titel :
Control and System Graduate Research Colloquium (ICSGRC), 2012 IEEE
Conference_Location :
Shah Alam, Selangor
Print_ISBN :
978-1-4673-2035-1
DOI :
10.1109/ICSGRC.2012.6287180
