Table 10 Objective comparison of OCRNet on public benchmark datasets.

From: OCRNet a robust deep learning framework for alphanumeric character recognition to assist the visually impaired

Dataset

Accuracy

Precision

Recall

F1-Score

MNIST

0.96

0.96

0.96

0.96

ICDAR 2013

0.95

0.94

0.92

0.93

ICDAR 2015

0.92

0.89

0.86

0.88

MLT 2017

0.89

0.87

0.82

0.84

Back to article page