SmartErasor

March 10, 2016

Overview

This project was the final project of the course EECS 332, Intro. to Computer Vision, at Northwestern University. The goal of this project was erasing a row of characters automatically and gradually while letting the background texture be unchanged.

Steps

• Find red region and get its average HSV value.
• Filter the image and get red areas in HSV space.
• Filter the pen’s tip and Get the minimum rectangle which can hold the pen’s tip.
• Kalman filter is added to estimate the pen tip position.