Documents scannerC++

OpenCV
Multiplatform Library

Project description

The application allows you to receive as input the photo of a surface containing a page (generic document) and output the scanned document. So first of all the page on the surface is identified, subsequently the edges are delimited so as to have only the region of interest available finally the outlined area is cut out and converted into black and white to obtain the final result scanned document.

chatroom

The operation of the application was created in C++ through use of the OpenCV library dedicated to real-time artificial vision. The weak points of the application are the lack of a graphical interface that allows for better interaction with the user.

View the code