Abstract
As the fundamental element of the Internet of Things, the QR code has become increasingly crucial for connecting online and offline services. Concerning e-commerce and logistics, we mainly focus on how to identify QR codes quickly and accurately. An adaptive binarization approach is proposed to solve the problem of uneven illumination in warehouse automatic sorting systems. Guided by cognitive modeling, we adaptively select the block window of the QR code for robust binarization under uneven illumination. The proposed method can eliminate the impact of uneven illumination of QR codes effectively whilst meeting the real-time needs in the automatic warehouse sorting. Experimental results have demonstrated the superiority of the proposed approach when benchmarked with several state-of-the-art methods.
Highlights
It is estimated that over 50 billion devices will be connected to the Internet by 2020
The automatic identification technology represented by two-dimensional code is one of the most critical technologies in the Internet of Things (IoT), which provides an entrance for the connection between the object and the network
Since the block window is closely related to the size of the position detection pattern, the proposed algorithm enhances the contrast of the QR code image to ensure the image finds the position detection pattern after preliminary binarization
Summary
It is estimated that over 50 billion devices will be connected to the Internet by 2020. The complex and variable lighting environment often leads to uneven illumination of the QR code Such nonuniform illumination affects the binarization and makes it difficult or inaccurate in identifying the QR code quickly and accurately. Put forward a method suitable for nonuniform illumination bar codes [10], but the algorithm is more complex and does not handle well the boundaries of uneven lighting. We propose a fast-adaptive thresholding method based on symbol features of the QR code for further improvement toward practical expectations from the industry. It solves the issues of long-time cost, poor adaptive ability, and low robustness.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have