DataMatrix code accurate locating based on boundary multi-features fusion

Parting at accurate locating challenges of Data Matrix code that polluted by abrasion, in this paper we present an extracting of best edges combination approach based on code boundary multi-features fusion. Firstly, transform DataMatrix code from image into Hough domain in which candidate boundary combinations be extracted. Afterwards, we design and extract four boundary features of the finder pattern of all candidate boundary combinations. Finally, merge the multi-features according to D-S theory, then make final locating decision base on the fusion result. The experimental results demonstrate the greater robustness and flexibility of our proposed approach to accurate detection of Data Matrix with c abrasion, compared with traditional methods.