AWS Kendra - Search PDF with handwritten text

Question

I have a scanned PDF with handwritten text and I am trying to search through it using AWS Kendra. However, Kendra doesn't search through the handwritten text. I tried using textract and comprehend, but there seem to be limitations to PDF size and number of pages with both services. Is there a way to allow Kendra to search through this handwritten text?

Accepted Answer

Textract would be your best bet - it's designed for handwriting recognition (among other things). Kendra is designed for language and meaning recognition. In super simplified terms, one is a convoluted neural network for images, the other is a recursive neural network for language; RNN works poorly for images, CNNs work poorly for language.

Textract does have limits - 3000 pages / 500MB for the pdf. Are you exceeding those limits?

Textract[ does have limits ](https://docs.aws.amazon.com/textract/latest/dg/limits.html)- 3000 pages / 500MB for the pdf.  Are you exceeding those limits?

AWS Kendra - Search PDF with handwritten text

Contenuto pertinente