A local Python document scanner built with OpenCV. It detects a document in a photo, corrects the perspective, enhances the scan, and can optionally extract text with OCR. This started as a course ...
POST /crop runs the canonical OpenCV document scanner pipeline (Canny → findContours → approxPolyDP → getPerspectiveTransform → warpPerspective) on the uploaded image. If a clean four-corner quad is ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results