Barcode detection using local analysis, mathematical morphology, and clustering

Abstract

Barcode detection is required in a wide range of real-life applications. Imaging conditions and techniques vary considerably and each application has its own requirements for detection speed and accuracy. In our earlier works we built barcode detectors using morphological operations and uniform partitioning with several approaches and showed their behaviour on a set of test images. In this work, those ideas have been extended with clustering, contrast measuring, distance transformation and probabilistic Hough transformation. Using more than one feature for localization leads to better accuracy, which makes detectors based on simple features, a competitive solution for commercial softwares and helps to fulfill the requirements of industrial applications even more.