Search code examples
modeling

Detect Page Layout using Machine Learning

i try to make An application that used to tag page something like HTML Pages

is there is a way using ML to detect and identify the layout of the page

Headers , tables , Footer

or it should only using AI Algorithms

can any one help me in this point

best reagrds

Solution

  • I used Faster RCNN referring to this Post https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10

    and it worked fine with me also i tried some other algorithm to enhance the result like RLSA you can refer to this also

    https://pypi.org/project/pythonRLSA/

    i couldn't copy a sample of my output is it relative to my business work but result is very optimistic

    hope help you