Title :
A Radial Neural Convolutional Layer for Multi-oriented Character Recognition
Author :
Cecotti, Hubert ; Vajda, Szilard
Author_Institution :
Dept. of Psychological & Brain Sci., Univ. of California, Santa Barbara, Santa Barbara, CA, USA
Abstract :
The recognition of fully multi-oriented handwritten characters is a challenging problem. Contrary to univariate signals where the shift invariance property in the Fourier transform can be used, multivariate signals like images require special care to extract rotation invariant features. Several strategies to solve such classification tasks are possible. The proposed method considers input features obtained by the Radon transform or Polar transform. A convolutional neural network is then used for extracting higher level features. This classifier includes in addition the Fast Fourier Transform for extracting shift invariant features at the neural network level. The Radon transform and the convolutional layers process the image at the pixel level while the Fourier transform and the upper layers of the neural network process rotation invariant features. The classifier is evaluated on multi-oriented handwritten digits based on the MNIST database (Arabic digits) and on the ISI database (Bangla digits). The average recognition rate for multi-oriented characters is 93.10% for the Arabic digits and 77.01% for the Bangla digits. This neural architecture highlights the interest of the radial convolutional layer for the recognition of multi-oriented shapes.
Keywords :
Radon transforms; fast Fourier transforms; feature extraction; handwritten character recognition; image classification; neural nets; Arabic digits; Bangla digits; ISI database; MNIST database; Polar transform; Radon transform; average recognition rate; classifier; convolutional neural network; fast Fourier transform; multioriented handwritten character recognition; multioriented handwritten digits; radial neural convolutional layer; rotation invariant feature extraction; shift invariant feature extraction; Biological neural networks; Character recognition; Databases; Feature extraction; Neurons; Transforms;
Conference_Titel :
Document Analysis and Recognition (ICDAR), 2013 12th International Conference on
Conference_Location :
Washington, DC
DOI :
10.1109/ICDAR.2013.137