AI for custom coding with image object detection

Me
Jan 13, 2023, 11:46 PM

Hi,

Please refer this project--
Grammarly API at https://developer.grammarly.com/

You have to use this API to feed in a folder containing PDF Files as input, and the Grammarly API will paraphrase the text and return a number of equivalent PDF files which will be saved to disk.

ALso refer this URL--> https://inside-machinelearning.com/en/use-yolov7/
YOu have to modify it so that it accepts a list of images in a folder and saves the output as an XML file. It gives list of objects in an image (OBject recognition).

Finally 3rd task is new-- go to an API, take output XML of previous step as input, and get as output (a) Images only (b) Illustrations only.

ANd 4th task-> PDF of step 1 has tags like img1.png and so on, simply insert output of 3rd step, which is img1.png of pdf(all images in a PDF one by one)-> 2nd step gives text based on the image--> 3rd step gives new images based on text ie objects in original image--> now insert all new images at placeholders for various images in PDF file.

THe main tasks are already coded as explained above. You have to combine these into a single Python project.


Do let me know if you can do this work.

Thanks,
Arvind.