A Skip-connected Multi-column Network for Isolated Handwritten Bangla Character and Digit recognition

Abstract

Finding local invariant patterns in handwrit-ten characters and/or digits for optical character recognition is a difficult task. Variations in writing styles from one person to another make this task challenging. We have proposed a non-explicit feature extraction method using a multi-scale multi-column skip convolutional neural network in this work. Local and global features extracted from different layers of the proposed architecture are combined to derive the final feature descriptor encoding a character or digit image. Our method is evaluated on four publicly available datasets of isolated handwritten Bangla characters and digits. Exhaustive comparative analysis against contemporary methods establishes the efficacy of our proposed approach.

References in corpus (5)

• Handwritten Bangla Basic and Compound character recognition using MLP and SVM classifier
• Multi-column Deep Neural Networks for Image Classification
• Handwritten Bangla Alphabet Recognition using an MLP Based Classifier
• An MLP based Approach for Recognition of Handwritten `Bangla' Numerals
• Bengali Handwritten Character Classification using Transfer Learning on Deep Convolutional Neural Network