Exploration of Deep Learning Based Recognition for Urdu Text

TL;DR

This paper presents a convolutional neural network-based system for recognizing Urdu text, addressing segmentation challenges and achieving high accuracy in component classification.

Contribution

The study introduces a CNN-based Urdu OCR system utilizing hierarchical classification and permutation-based dataset generation, improving recognition accuracy.

Findings

Achieved 99% accuracy in component classification.

Developed a dataset through permutation of characters.

Implemented a hierarchical neural network for recognition.

Abstract

Urdu is a cursive script language and has similarities with Arabic and many other South Asian languages. Urdu is difficult to classify due to its complex geometrical and morphological structure. Character classification can be processed further if segmentation technique is efficient, but due to context sensitivity in Urdu, segmentation-based recognition often results with high error rate. Our proposed approach for Urdu optical character recognition system is a component-based classification relying on automatic feature learning technique called convolutional neural network. CNN is trained and tested on Urdu text dataset, which is generated through permutation process of three characters and further proceeds to discarding unnecessary images by applying connected component technique in order to obtain ligature only. Hierarchical neural network is implemented with two levels to deal with three degrees of character permutations and component classification Our model successfully achieved 0.99% for component classification.