This program aims to detect tables/invoices from an image using an object-detection-YOLOv4-model and subsequently extract the available text-information by employing an OCR.
I worked on creating this program during a Hackathon conducted by IIT Madras.
The model is fine-tuned on a dataset using a dataset containing n? images. The dataset was split into training and validation. See notebook.ipynb for a complete code to train the model.
... Incomplete
text-extraction ... Incomplete ...