Recognition of noisy numerals using neuronal network
Mohd Yusoff Mashor, Siti Noraini Sulaiman · The International Journal of the Computer, the Internet and Management · 2001
Neural networks are known to be capable of providing good recognition rate at the present of noise where other methods normally fail. Neural networks with various architectures and training algorithms have successfully been applied for letter or character recognition. This paper uses MLP network trained using Levenberg-Marquardt algorithm to recognise noisy numerals. The recognition results of the noisy numeral showed that the network could recognize normal numerals with the accuracy of 100%, blended numerals at average of 95 numerals added with Gaussian noise at the average of 94% and partially deleted numerals at 81% accuracy.