Google vision API algorithm

Question

I was wondering how the google cloud vision works behind the scenes. What kind of algorithms are used for processing the images? Is there some texts explaining this?

Thanks to all

Answer 1

This might be a late answer, but adding it for future reference. As mentioned above the OCR is done through deep learning, especially the Convolutional Neural Networks. Do go though this blog by drop box on how they implemented their own OCR engine with similar workings.

https://blogs.dropbox.com/tech/2017/04/creating-a-modern-ocr-pipeline-using-computer-vision-and-deep-learning/