Will I need Spark NLP for Healthcare or Spark OCR to de-id burnt-in text on images? #335
-
I was hoping to use trained models to de-id burnt-in text on images. Will I need spark-nlp or does spark-ocr have tools? If I need spark-nlp, it doesn't seem that I would need spark-ocr since I only want to remove the text and not interested in deciphering it. Is this correct? |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
You will need to use Deid from sparknlp_jsl (licensed sparknlp).. since you can already extract the text from the images, you will now feed this to deid pipeline.. here is the example notebook: |
Beta Was this translation helpful? Give feedback.
You will need to use Deid from sparknlp_jsl (licensed sparknlp).. since you can already extract the text from the images, you will now feed this to deid pipeline.. here is the example notebook:
https://github.com/JohnSnowLabs/spark-ocr-workshop/blob/master/jupyter/SparkOcrDicomDeIdentification.ipynb