An Improved Sauvola Approach on QR Code Image Binarization
Yu Jie He, Yang Yang · 2019
The paper presents a novel QR code image binarization method to deal with uneven illumination. Our method is based on an adaptive local binarization approach proposed by J. Sauvola. For different illumination condition, it chooses different rule to select the threshold used to distinguish foreground and background. It can use adaptive window size based on lighting condition while calculating mean and standard deviation. The proposed method uses a specific dataset for evaluation and is compared across multiple methods. The experimental results show that the new binarization method can be done with high accuracy and stability, and it is obviously superior to the preceding ways.