Dynamic features based stroke recognition system for signboard images of Gurmukhi text

Abstract

The computation of correct features is an essential phase for efficient data representation and benchmarked accuracy in text recognition systems. The offline text lacks dynamic information regarding the writing order or nature of trajectories of stroke. Recovery of drawing order technique helps to retrieve trajectory of a stroke. This information aids in computing dynamic feature vector based on chain codes or trajectory points for text recognition. The present work proposes a dynamic feature extraction approach based on recovery of drawing order to understand scene text in Indic script Gurmukhi. An inhouse dataset of strokes was obtained from 820 real time Gurmukhi signboard images. Stroke recognition was performed using Conv1D, SVM and HMM classifiers. Best recognition results were achieved using SVM and Conv1D as 82.88% and 84.67%. The major objective of present study is to propose dynamic features based recognition scheme for Indic scripts signboard images suitable for real-life applications.