# Interactive bounding boxes using Tesseract

**URL:** <https://community.labelstud.io/t/interactive-bounding-boxes-using-tesseract/581>\
**Category:** Label Studio Support\
**Created:** [June 22, 2025, 3:35pm UTC](https://community.labelstud.io/t/interactive-bounding-boxes-using-tesseract/581 "2025-06-22T15:35:00Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![gamba99](https://avatars.discourse-cdn.com/v4/letter/g/f19dbf/32.png) [@gamba99](https://community.labelstud.io/u/gamba99)\
**Post date:** [June 22, 2025, 3:35pm UTC](https://community.labelstud.io/t/interactive-bounding-boxes-using-tesseract/581/1 "2025-06-22T15:35:00Z")

</div>

Hello!  
I am following this tutorial to configure live annotation with Tesseract: [Label Studio Enterprise Documentation — Interactive bounding boxes OCR in Label Studio with a Tesseract backend](https://docs.humansignal.com/tutorials/tesseract)  
I am using Docker on my Windows machine and want to use local storage.  
I imported my images directly to Label Studio with the import file dialog.  
I started labelstudio with:  
` docker run -it -p 8080:8080 -v ${PWD}/mydata:/label-studio/data --env LABEL_STUDIO_LOCAL_FILES_SERVING_ENABLED=true --env LABEL_STUDIO_LOCAL_FILES_DOCUMENT_ROOT=/label-studio/data/images heartexlabs/label-studio:latest label-studio --log-level DEBUG` In the example.env file in the Label Studio ML Backend, I set  
`LABEL_STUDIO_HOST=` `http://host.docker.internal:8080` and the API key accordingly.  
I start the Backend with: `docker compose up tesseract`  
Then I connected the model with the URL and tested the Tesseract connection and it is returning a good response of “200".  
The “Auto-detect” button appears as expected.  
However, when I click it, I **cannot draw any boxes manually**.  
Is there something I’m missing?  
Thanks a lot in advance!