A Large-Scale VR Panoramic Dataset of QR Code and Improved Detecting Algorithm

Abstract

With the rapid development of mobile payment and scanning technology, QR code has become widespread in both consumer and enterprise domains. However, there is the lack of corresponding research on detecting QR code in panoramic video due to the lack of high-quality datasets. To fill this gap, in this work we propose a large-scale panoramic QR code dataset to facilitate relevant research. Our dataset includes the following characteristics: (1) It is by far the largest dataset in terms of image quantity. (2) Compared with the existing datasets, ours is closer to the realistic setting and can derive a variety of research problems. In addition to the dataset, we propose a QR code detecting approach in a complex environment based on deep learning improving accuracy of QR code detection.