Binarization of Nonuniform Illumination Barcode

Abstract

This paper proposes a novel binarization approach, appropriate for nonuniform illumination barcode. The proposed method firstly clusters pixels of the image into two categories, which is black and white. Next, the variations of these two parts are calculated and binarization is conducted in the part with less variation. Finally, the uneven illumination part is established and recovered in the part with greater variation through both gray-value information and spatial information. The experimental results show that the proposed approach is effective for the uneven illumination barcode.