A Fast Hough Transform Approximation and Its Application for Barcode Localization

Abstract

This paper addresses barcode localization in images acquired by wireles cameras. For this purpose, a fast Hough transform approximation by use of a sliding mask is developed. The approximation decomposes the lines at different orientations into distinct bitplanes. Barcode localization is achieved by considering the high density locations in the bitplanes via morphology and profiling. The time complexity of the proposed approximation is lower than the previously proposed fast Hough transform, though it achieves the equal performance in localization of barcodes.