Hits:

Indexed by:会议论文

Date of Publication:2016-01-04

Included Journals:EI

Volume:9517

Page Number:79-90

Abstract:The barcode is widely used in logistics, identification, and other applications. Most of the research and applications now focus on how to decode the barcode. However, in a complex situation, the barcode is difficult to locate accurately. This paper presents an algorithm that can effectively detect the locations of multiple barcodes. First, image texture features are extracted by combining the local binary pattern (LBP) and gray histogram, and then a machine learning algorithm is applied to create a classifier by using the support vector machine (SVM) to extract and train the positive and negative samples. Second, the Hough transform is applied to the input image to achieve the angle invariable. Finally, our proposed method has been evaluated by the WWU Muenstar Barcode Database and the experimental results show that the proposed result has higher performance than other methods. © Springer International Publishing Switzerland 2016.