Skip to main content

Table 3 Text detection results on three experimental scenarios using different models

From: Detection and recognition of cursive text from video frames

Models Scenario Precision Recall F-Measure
SSD S-I 79.7 66.9 72.7
  S-II 75.3 56.1 64.3
  S-III 80.3 70.5 75.1
Faster R-CNN S-I 83.1 84.9 84.0
  S-II 74.7 67.6 71.0
  S-III 86.9 89.8 88.3
East S-I 78.2 45.3 57.3
  S-II 70.4 47.7 56.9
  S-III 77.3 47.9 59.1