The script scans the image from your camera and detects if any document is available in frame.
After detection of the doc, the image is cropped with the document in focus and an orthogonal projection is constructed.
The detection is peformed considering the view as an image and all information processed is through image processing utilising OpenCV.
Converting the image in pdf format ==> Feature added
- Adding OCR and text extraction from the scanned copy. need to understand if extracting text from pdf or image would be better