This repository lets you train neural networks models for performing end-to-end full-page handwriting recognition using the Apache MXNet deep learning frameworks on the IAM Dataset.
Apache License 2.0
481
stars
189
forks
source link
How can we increase the recognising accuracy for capital letter text and for digits because for capital letters and digits it is not even 10%? #32
Hi @Neelesh1121, unfortunately this will likely require a more comprehensive dataset. The IAMdataset does not provide vast amounts of capital letters and digits.
You could potentially create your own dataset with online handwritten text recognition datasets (e.g., IAM) or single character datasets (e.g., mnist).
Hi @Neelesh1121, unfortunately this will likely require a more comprehensive dataset. The IAMdataset does not provide vast amounts of capital letters and digits.
You could potentially create your own dataset with online handwritten text recognition datasets (e.g., IAM) or single character datasets (e.g., mnist).