Urdu Ligature Recognition System: An Evolutionary Approach

Cursive text recognition of Arabic script-based languages like Urdu is extremely complicated due to its diverse and complex characteristics. Evolutionary approaches like genetic algorithms have been used in the past for various optimization as well as pattern recognition tasks, reporting exceptional results. The proposed Urdu ligature recognition system uses a genetic algorithm for optimization and recognition. Overall the proposed recognition system observes the processes of pre-processing, segmentation, feature extraction, hierarchical clustering, classification rules and genetic algorithm optimization and recognition. The pre-processing stage removes noise from the sentence images, whereas, in segmentation, the sentences are segmented into ligature components. Fifteen features are extracted from each of the segmented ligature images. Intra-feature hierarchical clustering is observed that results in clustered data. Next, classification rules are used for the representation of the clustered data. The genetic algorithm performs an optimization mechanism using multi-level sorting of the clustered data for improving the classification rules used for recognition of Urdu ligatures. Experiments conducted on the benchmark UPTI dataset for the proposed Urdu ligature recognition system yields promising results, achieving a recognition rate of 96.72%.