I'm working on a project that involves extracting the statement and geometric figures in a mathematics exercise. From a picture taken of the exercise, it is necessary to develop an algorithm that extracts the text on the one hand, and on the other hand the type of figures: triangle, rectangle, etc. but also the name of the figure, as well as the lengths of the segments and angles present in the figure.
Code and application should be developed on Android and iOs, using ocr and image processing (opencv library preferably) otherwise any other proposal would be discussed.
Thank you for you submit.