计算机科学与探索 ›› 2021, Vol. 15 ›› Issue (2): 338-345.DOI: 10.3778/j.issn.1673-9418.2004014

• 图形图像 • 上一篇    下一篇

复杂环境下基于边缘扩张的条形码定位方法

艾达,马宇豪,刘颖,郭建林,周光军   

  1. 1. 西安邮电大学 电子信息现场勘验应用技术公安部重点实验室,西安 710121
    2. 深圳市有方科技股份有限公司,广东 深圳 518109
  • 出版日期:2021-02-01 发布日期:2021-02-01

Edge-Based Expansion Method for Barcode Locating Under Complicated Environments

AI Da, MA Yuhao, LIU Ying, GUO Jianlin, ZHOU Guangjun   

  1. 1. The Key Laboratory of Electronic Information Application Technology of Site-Survey of the Ministry of Public Security, Xi'an University of Posts and Telecommunications, Xi'an 710121, China
    2. Neoway Technology Co., Ltd., Shenzhen, Guangdong 518109, China
  • Online:2021-02-01 Published:2021-02-01

摘要:

条形码识别技术已广泛应用于人们日常生活和工业生产中。针对基于图像处理的条形码定位和识别过程中会受到光照环境、画面内容、镜头对焦等因素的影响导致识别效果不理想的问题,提出了一种利用边缘特性对条形码图像进行扩张处理与判别的定位方法。首先使用改进的Sobel算子提取图像的边缘特征,对条形码边缘进行区域扩张处理,以增大连通性;然后应用图像中连通区域的形状特征对条形码区域进行判别;最后应用Radon变换对倾斜的条形码进行校正以利于条形码识别。实验结果显示,提出方法在公开数据集的对比实验中定位准确率有显著提升。在智能手机应用中,通过定位条形码区域,使得解码运算量降低,识别时间平均减少26.1%,较好地满足了实际应用的需求。

关键词: 图像处理, 边缘提取, 边缘区域扩张, Radon变换, 条形码定位

Abstract:

Barcode recognition technology has been widely used in people??s daily life and industrial production. Barcode locating and recognition based on image processing are affected by light environment, image content, lens focus and other factors. It will lead to inaccurate identification. A method of edge-based expansion for barcode locating is proposed according to edge characteristics. Firstly, the modified Sobel operator is used to extract the edges in the image and these edges are extended to advance the connectivity. After that, barcode area is distin-guished by the shape features of the image??s connected area. Finally, slanted barcode is corrected using Radon trans-form to improve the recognition performance. The experimental results show that the locating accuracy of proposed method is significantly improved on public datasets. In the application of smart phones, the decoding operation is reduced by positioning the barcode area and the recognition time is decreased by 26.1% on average, which meets the needs of practical applications better.

Key words: image processing, edges extracting, edge-based expansion, Radon transform, barcode locating