Handwritten Text Recognition (HTR) system implemented with TensorFlow (TF) and trained on the IAM off-line HTR dataset. This Neural Network (NN) model recognizes the text contained in the images of segmented words.
Download the zip and unzip it. Place the code in your drive under /content/drive folder.
There is colab notebook named as Handwritten_Text_Recognition.ipynb open that file and run it.
python main.py Validation character error rate of saved model: 10.624916% Init with stored values from ../model/snapshot-38 Recognized: "little" Probability: 0.96625507
Recognized: "MR." Probability: 0.57650965