Building an image processing pipeline with Python


Video is ready, Click Here to View ×

Franck Chastagnol
This talk covers the details of how to build a highly scalable image processing pipeline using Python and third-party open source libraries and tools such as OpenCV, NumPy, Tesseract, ImageMagick, Tornado, Nginx and MySQL.

12 thoughts on “Building an image processing pipeline with Python

  1. Tesseract out of the box is only like 70% accurate for me on b&w 300 dpi scans ;/ not sure how to "precision train" it. Feels like it should do better out of box tbh.. maybe need to do some image preprocessing which is what brought me here

  2. Wow, judging by the screen shot, this is timely. I have a load of till rolls to process for an accounting fraud case. I was going to restrict my report to the Z (end of day) readings from the till but if I can get the transactions I might be able to correlate them with the dispense logs.

Leave a Reply

Your email address will not be published. Required fields are marked *