An improved binarization algorithm of QR code image

The nonuniform illumination QR code image would present all white or all black error areas after global binarization processing. Pseudo-boundary would appear in the processing of local binarization, and the calculation would take long time. This paper puts forward an improved background gray-level based binarization algorithm for the nonuniform illumination QR code image. Firstly, doing sub-block processing according to the size of the QR code image. On this basis, using gray-level estimation formula for computing the gray-level value of each block. Secondly, using joint interpolation algorithm to build the background gray-level image. Then using the background gray-level image to adapt the original image to get the corrected image. Finally, using the Otsu algorithm for the corrected image binarization. Experiments show that the algorithm can do effective correction to uneven illumination QR code image, get a good binary image.