Deep learning based-approach for quick response code verification

Quick response (QR) code-based traceability is considered as a smart solution to know details about the origin of products, from production to transportation and preservation before reaching customers. However, the QR code is easily copied and forged. Thus, we propose a new approach to protect this code from tampering. The approach consists of two main phases like hiding a security feature in the QR code, and estimating the similarity between the QR code affixed on the product and the genuine ones. For the former issue, the secret feature is encoded and decoded by using error correcting code for controlling errors in noisy communication channels. Hiding and extracting the encoded information in the QR code are conducted by utilizing a deep neural network in which the proposed network produces a watermarked QR code image with good quality and high tolerance to noises. The network is capable of robustness against real distortions caused by the process of printing and photograph. For the later issue, we develop neural networks based upon the architecture of Siamese network to measure the similarity of QR codes. The secret feature extracted from the obtained QR code and the result of QR code similarity estimation are combined to determine whether a QR code is genuine or fake. The proposed approach gives a competitive performance, with an average accuracy of 98%, and it has been applied to QR code authentication in practice.