Deep learning models that take a document image file as input, locate the position of paragraphs, lines, images, etc. with their labels and confidence scores.
-Inspiration from the blog- https://medium.com/@Intellica.AI/a-comparative-study-of-custom-object-detection-algorithms-9e7ddf6e765e
Yolov3, FasterRCNN & SSD are broadly top 3 model architectures that are used for Object detection. So, for this task, prediction and confidence on inference images of these 3 architectures have been compared.