Reading Multilevel 2-D Barcodes Using a Machine Learning Approach

Jiaheng Zhang, Junjie Chen, Le Ou-Yang, Changsheng Chen, Ning Xie

Abstract: This article addresses the reading problem of multilevel 2-D barcodes over a print-and-capture (PC) channel. The prior reading schemes have different limitations to hinder their applications, e.g., suffering from quantization error, being sensitive to the predetermined decision boundaries, and being sensitive to the selection of initial parameters. In this article, we introduce a machine learning approach to address the above limitations using a new ensemble clustering (EC) algorithm. Based on the new EC algorithm, we propose two reading schemes of a multilevel 2-D barcode. Specifically, the first proposed scheme is named the EC reading scheme. In the EC reading scheme, we introduce a weighted ensemble mechanism to assign different weights to different base clustering results. Then, we propose the second scheme, named the enhanced EC (EEC) reading scheme, to further improve the reading performance with the help of the reference symbols. We implement our approach and conduct extensive performance comparisons through an actual excremental platform under various multilevel 2-D barcodes and various capturing devices. From experimental results, we observe that both proposed reading schemes have better performance than the prior reading schemes. Moreover, the EEC reading scheme has better performance than the EC reading scheme, and their performance gap becomes more apparent as the distortion of a PC channel increases.