The QR-code reorganization in illegible snapshots taken by mobile phones

In this paper, we give an algorithm for the analysis and correction of the distorted QR barcode (QR-code) image. The introduced algorithm is based on the code area finding by four corners detection for 2D barcode. We combine Canny edge detection with contours finding algorithms to erase noises and reduce computation and utilize two tangents to approximate the right-bottom point. Then, we give a detail description on how to use inverse perspective transformation in rebuilding a QR-code image from a distorted one. We test our algorithm on images taken by mobile phones. The experiment shows that our algorithm is effective.