Table 15 Accuracy of the three algorithms.

From: Integrated framework utilizing scene text detection and recognition techniques for enhancing point of interest extraction from name boards in all Indic languages

Language

Accuracy

Beam search

Greedy search

Levenshtein distance

Bengali

7%

65%

65%

Gujarati

4%

89%

89%

Kannada

1%

70%

70%

Odia

7%

57%

57%

Tamil

1%

90%

90%

English

36%

36%

36%

Hindi

8%

84%

84%

Malayali

5%

43%

43%

Punjabi

8%

92%

92%

Telugu

1%

79%

79%