(Choose 2 answers)
A. If we conclude that the character recognition's errors are mostly due to the character recognition system having high variance, then it may be worth significant effort obtaining additional training data for character recognition.
B. We should dedicate significant effort to collecting additional training data for the text detection system
C. The least promising component to work on is the character recognition system, since it is already obtaining 100% accuracy.
D. Performing the ceiling analysis shown here requires that we have ground-truth labels for the text detection, character segmentation and the character recognition systems.
Suppose you have a PhotoOCR system, where you have the following pipeline:
Image
Text detection
Character segmentation
Character recognition
You have decided to perform a ceiling analysis on this system, and find the following:
Component
Accuracy
Overall System 70%
Text Detection 72%
Character Segmentation 82%
Character Recognition 100%
Which of the following statements are true?
E39
