rajesh-bhat / spark-ai-summit-2020-text-extraction

Update Dec 8th:

Speaking at Open Data Science Conference (ODSC): https://odsc.com/speakers/text-extraction-from-images-using-deep-learning-techniques/

Update 24th Aug

Report published at Weights & Biases: https://app.wandb.ai/authors/text-recognition-crnn-ctc/reports/Text-Recognition-with-CRNN-CTC-Network--VmlldzoxNTI5NDI

Refer to CRNN_CTC_wandb.ipynb for the code: https://github.com/rajesh-bhat/spark-ai-summit-2020-text-extraction/blob/master/CRNN_CTC_wandb.ipynb

Spark AI Summit

For PPT refer to : Slides_for_Spark_AI_TE.pdf

Dataset used for training text recognition model: Subset of MJSYNTH (https://www.robots.ox.ac.uk/~vgg/data/text/mjsynth.tar.gz )

Code for Text Recognition: refer to CNN_LSTM_CTC.ipynb

YouTube link: https://www.youtube.com/watch?v=kURGWG1yIxs

spark-ai-summit-2020-text-extraction's Issues

Possible to share the dataset?

issue with unzip the mjsynth_sample.zip

End-of-central-directory signature not found. Either this file is not
a zipfile, or it constitutes one disk of a multi-part archive. In the
latter case the central directory and zipfile comment will be found on
the last disk(s) of this archive.
unzip: cannot find zipfile directory in one of /content/mjsynth_sample.zip or
/content/mjsynth_sample.zip.zip, and cannot find /content/mjsynth_sample.zip.ZIP, period.

Invalid Argument Error