watersink/ocrsegment

a deep learning model for page layout analysis / segmentation.

OCR Segmentation

a deep learning model for page layout analysis / segmentation.

dependencies

tensorflow1.8

python3

dataset:

uw3-framed-lines-degraded-000

make training labels

python3 data_pre_process.py

train

python3 train_test.py

test

python3 segmentation.py

references

Multi-Dimensional Recurrent Neural Networks
Robust_ Simple Page Segmentation Using Hybrid Convolutional MDLSTM Networks
https://github.com/NVlabs/ocroseg
https://github.com/philipperemy/tensorflow-multi-dimensional-lstm