Hi, I was following this article on how to perform text detection and recognition. When I tested the script out on my computer it worked fine and I was able to get results. However, I tested on the Jetson Nano, the EAST text detector was able to detect the text but the tesseract OCR failed to get any results, which doesn’t make sense because it got results on the same image on my computer.
Could you list the library you used for both EAST and OCR? Ex. TensorFlow.
If you deploy the model with TensorFlow-like frameworks, the result should be the same between desktop and Jetson.
A possible reason is from the software version.
Some compatibility issue may occur if the model and framework are different in the version.
I installed tesseract with sudo apt install tesseract-ocr. Then I got access in python through the pytesseract library.
There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
We want to reproduce this issue in our environment.
Could you share the detailed steps so we can give it a closer check.