Using compatible shape descriptor for lexicon reduction of printed Farsi subwords

TL;DR

This paper introduces a neural network-based approach for selecting shape descriptors tailored to individual printed Farsi subwords, improving lexicon reduction by handling diverse shape complexities effectively.

Contribution

It proposes a novel method that dynamically selects shape descriptors for Farsi subwords using a neural network, enhancing lexicon reduction accuracy.

Findings

Effective shape descriptor selection improves lexicon reduction.

Method adapts to diverse subword shapes.

Demonstrated success on Persian subword dataset.

Abstract

This Paper presents a method for lexicon reduction of Printed Farsi subwords based on their holistic shape features. Because of the large number of Persian subwords variously shaped from a simple letter to a complex combination of several connected characters, it is not easy to find a fixed shape descriptor suitable for all subwords. In this paper, we propose to select the descriptor according to the input shape characteristics. To do this, a neural network is trained to predict the appropriate descriptor of the input image. This network is implemented in the proposed lexicon reduction system to decide on the descriptor used for comparison of the query image with the lexicon entries. Evaluating the proposed method on a dataset of Persian subwords allows one to attest the effectiveness of the proposed idea of dealing differently with various query shapes.