QR code detection using deep learning models

• Grant number: 18/00390-7
• Support Opportunities: Scholarships in Brazil - Master
• Start date: December 01, 2018
• End date: August 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Nina Sumiko Tomita Hirata
• Grantee: Leonardo Blanger
• Host Institution: Instituto de Matemática e Estatística (IME). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery, AP.TEM
• Associated scholarship(s): 19/17312-1 - Adversarial learning of image augmentation policies for object detection, BE.EP.MS

Abstract

QR Codes are two-dimensional codes which are capable of encoding not only digits, as it is the case with traditional barcodes, but also alphanumeric characters. Among their most common uses, it is worth mention the URL encoding and fast access to the referred web content through the use of decoding applications. When these codes are explicitly framed and captured, the decoding process happens without major issues. However, QR codes that are accidentally captured, without explicit intention, are often not even detected. The possibility of detecting these codes could make feasible, for instance, applications that use autonomous robots in dynamic environments. In this research project, deep learning based methods for detecting the presence of QR codes on arbitrarily acquired images will be studied and developed. Strategies that explore the common structure of QR codes, such as the fixed patterns in their three corners, will be proposed. As concrete contributions, it is expected the production of a dataset for the training and the evaluation of detectors, deep models specifically trained for the detection of these codes, and the promotion and advancement of knowledge within the research group regarding deep models for object detection in images. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BLANGER, LEONARDO; HIRATA, NINA S. T.; JIANG, XIAOYI; IEEE COMP SOC. Reducing the need for bounding box annotations in Object Detection using Image Classification data. 2021 34TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2021), v. N/A, p. 8-pg., 2021-01-01. (18/00390-7, 15/22308-2, 17/25835-9, 19/17312-1)

BLANGER, LEONARDO; HIRATA, NINA S. T.; IEEE. AN EVALUATION OF DEEP LEARNING TECHNIQUES FOR QR CODE DETECTION. 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), v. N/A, p. 5-pg., 2019-01-01. (17/25835-9, 18/00390-7, 15/22308-2)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

BLANGER, Leonardo. An analysis of sample synthesis for deep learning based object detection. 2020. Master's Dissertation - Universidade de São Paulo (USP). Instituto de Matemática e Estatística (IME/SBI) São Paulo.