Deep Learning Approaches Based Robust QR Code Extraction and Verification for Industrial IoT

Quick Response (QR) codes are essential in industries like digital payments and ticketing, especially with advancements in deep learning and the Industrial Internet of Things (IoT). However, challenges persist in pattern extraction and authentic QR code verification, particularly in dynamic environments. Traditional methods struggle with issues such as poor lighting, complex backgrounds, and advanced counterfeits, leading to compromised accuracy. This study introduces an enhanced method for QR code extraction, named Adaptive Morphological Contour-Based QR Code Extraction (AMCQE) along with robust QR verification. Our approach addresses the limitations of conventional methods, ensuring accurate extraction and verification even under challenging conditions. Experimental results demonstrate excellent performance, achieving 99.28% accuracy and a processing time of 0.08 s. The deep learning model effectively differentiates authentic QR codes from counterfeits, underscoring the technique’s applicability in modern applications.