# Technical Architecture

The Document Understanding Subnet's technical architecture is designed to provide precise and efficient checkbox-text extraction, leveraging a combination of advanced object detection and OCR technologies. 

The architecture consists of two primary modules: the YOLO Checkbox Detector, based on the YOLOv8 object detection model, and the Tesseract OCR engine, both of which contribute to a robust, high-performance document processing pipeline.

{% content-ref url="technical-architecture/checkbox-text-extraction-yolo-checkbox-detector" %}
[checkbox-text-extraction-yolo-checkbox-detector](https://tatsu.gitbook.io/document-understanding-whitepaper/technical-architecture/checkbox-text-extraction-yolo-checkbox-detector)
{% endcontent-ref %}

{% content-ref url="technical-architecture/ocr-engine-tesseract-ocr" %}
[ocr-engine-tesseract-ocr](https://tatsu.gitbook.io/document-understanding-whitepaper/technical-architecture/ocr-engine-tesseract-ocr)
{% endcontent-ref %}

{% content-ref url="technical-architecture/workflow-of-checkbox-text-extraction" %}
[workflow-of-checkbox-text-extraction](https://tatsu.gitbook.io/document-understanding-whitepaper/technical-architecture/workflow-of-checkbox-text-extraction)
{% endcontent-ref %}