Data Extraction OCR -- 2

I just need model with source code explanation and model performance metrics (not looking for end to end project or UI)

I have unstructured pdfs with scanned data, I want convert it into image and improve image quality.

- text skewed in angle in 3d (rotation , curved etc)

- images with different light conditions, and quality

- images with different sizes

Perform ocr and extract fields like below with confidence score

Vendor/Company Name

Address (Shipping/Billing)

TAX

SubTotal

Total

If new field needs to be extracted I should be able to do with some code modification (Instruction Required)

I have very few samples (dataset)

No third party (paid) api should be called, it should be built purely in tensorflow..