Neural Process Lett (2008) 28:97–111
DOI 10.1007/s11063-008-9084-y
Robust Handwritten Character Recognition
with Features Inspired by Visual Ventral Stream
Ali Borji · Mandana Hamidi · Fariborz Mahmoudi
Published online: 31 August 2008
© Springer Science+Business Media, LLC. 2008
Abstract This paper focuses on the applicability of the features inspired by the visual
ventral stream for handwritten character recognition. A set of scale and translation invariant
C2 features are first extracted from all images in the dataset. Three standard classifiers kNN,
ANN and SVM are then trained over a training set and then compared over a separate test set.
In order to achieve higher recognition rate, a two stage classifier was designed with different
preprocessing in the second stage. Experiments performed to validate the method on the well-
known MNIST database, standard Farsi digits and characters, exhibit high recognition rates
and compete with some of the best existing approaches. Moreover an analysis is conducted
to evaluate the robustness of this approach to orientation, scale and translation distortions.
Keywords Optical character recognition · Handwritten character recognition ·
Visual system · Visual ventral stream · HMAX · C2 features
1 Introduction
Handwritten character recognition is still a challenging problem for many languages like
Farsi, Chinese, English, etc. Developing robust optical character recognition (OCR) tech-
niques would be very rewarding in today technology. Some of the successful applications
A. Borji (B )
School of Cognitive Sciences, Institute for Studies in Theoretical Physics and Mathematics,
Niavaran Bldg., P. O. Box 19395-5746, Tehran, Iran
e-mail: borji@ipm.ir
M. Hamidi
Computer and Information Technology Department, Azad University Branch of Zarghan,
Booali Boulevard, Azad University Street, P. O. Box 73415-314, Zarghan, Iran
F. Mahmoudi
Computer, Engineering and Information Technology Department, Azad University Branch of Qazvin,
Qazvin, Iran
123