Handwritten-text recognition

In this case study, we will be working toward transcribing the handwritten images so that we extract the text that is present in the pictures.

A sample of the handwriting looks as follows:

Note that in the preceding diagram, the handwritten characters have varied length, the images are of different dimensions, the separation between the characters is varied, and the images are of different quality.

In this section, we will be learning about using CNN, RNN, and the CTC loss function together to transcribe the handwritten examples.

Get Neural Networks with Keras Cookbook now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.