Python: OCR -> SPACY, NLP, TIKA, TABULA, pytesseract
We have a project that reads invoices We have used the above libraries and coded. We can OCR detect all text, but wee now need to do some text/key word value mapping. The values we must map is in the attached file. We planned to do AWS textract previously but now we decided to do it ourselves.
please see these documents for details of key pairing values and more document information
|Workload||40 hours/week , 100% onsite|
|Expected start date||ASAP|
|Expected end date||Open|
|Necessary skills||NLP, OCR, Python|