检索结果-内蒙古大学图书馆

Anti-tampering method of qr code hidden information based on deep learning

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第4期19卷 1-12页

作者： Wang, Nan Zhang, Lina Jiang, Tian Shen, Tengfei Anyang Normal Univ Sch Comp & Informat Engn Xian Ge Ave Anyang 455000 Henan Peoples R China Anyang Normal Univ Int Joint Res Lab Percept Data Intelligent Proc He Xian Ge Ave Anyang 455000 Henan Peoples R China Xian Univ Sci &Technol Coll Comp Sci & Technol Shangu Ave Xian 710699 Shaanxi Peoples R China

qr codes have gained widespread adoption across various industries for their large data capacity, rapid scanning speed, and robust error correction capabilities. However, they also face security risks, such as being copied or forged, which can lead to information leakage. To address these challenges, this paper proposes a qr code information hiding and tamper-proof mechanism that integrates convolutional neural network and twin networks. This mechanism designs and implements a robust and invisible information watermark embedding method using deep learning algorithms. It also constructs a similarity evaluation model based on twin networks for watermark extraction, accurately judging the authenticity of qr codes and effectively resisting forgery and tampering. In the analysis of the experimental results, the normalization factor between the original qr code image and the qr code image with embedded secret information reached over 0.99, and the Peak Signal-to-Noise Ratio exceeded 42 dB, significantly demonstrating the invisibility of the secret information. In robustness evaluations, the qr code can withstand Gaussian noise and image pollution attacks up to 30% without affecting the extraction of secret images. In the similarity assessment of secret images, the normalization coefficient and Peak Signal-to-Noise Ratio exceed 0.99 and 37 dB, respectively. Furthermore, the similarity between the original secret image and the extracted secret image, as detected by the twin network, exceeds 0.99, fully highlighting the superiority of this scheme. This approach is both effective and practical in ensuring the information security of qr codes, offering a novel solution for their secure application. The code is available at the following https://***/JCandyGold/CNN_qr_watermarks.

关键词： Deep learning Convolutional neural network Information hiding qr code Twin network

来源：评论

学校读者我要写书评

暂无评论

qrCrop: A qr code-Based Edge-Cloud Framework for Crop Yield Prediction 3rd

QRCrop: A QR Code-Based Edge-Cloud Framework for Crop Yield ...

引用

3rd International Conference on Network Security and Blockchain Technology

作者： Dey, Tanushree Bera, Somnath Mukherjee, Anwesha Roy, Samarjit De, Debashis Maulana Abul Kalam Azad Univ Technol Ctr Mobile Cloud Comp Dept Comp Sci & Engn BengalNH-12SimhatHaringhata Nadia 741249 W Bengal India Mahishadal Raj Coll Dept Comp Sci Mahishadal 721628 W Bengal India Eastern Int Univ Sch Comp & Informat Technol Nam Ky Khoi Nghia StHoa Phu Ward Thu Dau Mot City Vietnam

ISBN: (纸本)9789819780501;9789819780518

In this paper, a crop yield prediction system is proposed based on qr code and edge-cloud framework. In traditional systems, the cloud is used for IoT data analysis and storage. The concerns over the cloud-only system include security, latency, energy consumption, etc. The use of edge-cloud computing deals with the problem of latency and energy consumption. Nevertheless, the security is still amajor concern. In the proposed system, the user uploads soil and environmental parameters' data to the edge server using qr code to achieve secure data transmission. The data are analyzed using gated recurrent unit and long short-term memory network, and the result is sent to the cloud, from which the user can access the result anytime, anywhere. From the results, we observe that the proposed framework reduces the latency and energy consumption by similar to 28% than the cloud-only framework. The results also demonstrate that the proposed framework has an accuracy of similar to 99% in crop yield prediction.

关键词： qr code Deep learning Crop yield prediction Energy Latency

来源：评论

学校读者我要写书评

暂无评论

Self-Reported Pesticide Application, Access to Pesticide Labels, and qr code Use Among Agricultural H-2A Workers, North Carolina, 2024

引用

AMERICAN JOURNAL OF INDUSTRIAL MEDICINE 2025年第4期68卷 388-392页

作者： Asuaje, Cesar Lee, Joseph G. L. Nusrat, Nowrin Andres, Lilibeth Rivera, Natalie D. Connaughton-Espino, Tania Janampa, Paul Leprevost, Catherine E. Univ Florida Inst Food & Agr Sci Extens W Palm Beach FL USA Wake Forest Univ Sch Med Dept Implementat Sci Div Publ Hlth Sci Winston Salem NC USA NC State Univ Coll Agr & Life Sci Dept Appl Ecol Raleigh NC 27695 USA NC Dept Hlth & Human Serv NC Farmworker Hlth Program Off Rural Hlth Raleigh NC USA

BackgroundDespite the composition of the United States' agricultural workforce and the sector's reliance on Spanish-speaking migrant labor, pesticide labels are largely available in English only. Currently, federal regulators are considering strategies to provide pesticide label information access in Spanish via a qr code or through other electronic methods on the pesticide container. Data on access to labels and the use of qr codes among agricultural workers are limited. We provide policy-relevant findings from surveys collected at a large agricultural worker H-2A visa arrival *** April and May 2024, we verbally administered Spanish-language, in-person surveys in North Carolina (n = 160). We asked questions about pesticide use, access to labels, and qr code use as well as age, gender, and seasons worked in the United *** analyses revealed approximately 60% of workers had not used a qr code. Among participants who had used pesticides and worked for two or more seasons (42%), approximately 30% reported not having access to the label on the *** survey findings show qr-code-based pesticide labels will reach a subset of workers, but substantial gaps will remain.

关键词： agricultural workers agriculture pesticide pesticide labeling qr code

来源：评论

学校读者我要写书评

暂无评论

Effect on Response Rates of Adding a qr code to Patient Consent Forms for Qualitative Research in Patients With Cancer: Pilot Randomized Controlled Trial

引用

JMIR FORMATIVE RESEARCH 2025年 9卷 e66681页

作者： Wyse, Rebecca Forbes, Erin Norton, Grace Da Silva, Priscilla Viana Fakes, Kristy Johnston, Sally Ann Smith, Stephen R. Zucca, Alison Univ Newcastle Sch Med & Publ Hlth Univ Dr Callaghan NSW 2308 Australia Hunter Med Res Inst New Lambton Hts NSW Australia John Hunter Hosp Hunter New England Local Hlth Dist New Lambton Hts NSW Australia

Background: The successful conduct of health and medical research is largely dependent on participant recruitment. Effective, yet inexpensive methods of increasing response rates for all types of research are required. qr codes are now commonplace, and despite having been extensively used to recruit study participants, a search of the literature failed to reveal any randomized trial investigating the effect of adding a qr code on qualitative research response rates. Objective: This study aimed to collect data on rates of response, consent, and decline among patients with cancer, and the average time taken to respond following randomization to receive either a qr code or no qr code on the patient consent form for a qualitative research study. Methods: This was a pilot randomized controlled trial (RCT) embedded within a qualitative research study. In total, 40 eligible patients received a recruitment pack for the qualitative study, which included an information statement, a consent form, and an addressed, stamped envelope to return their consent form. Patients were randomized 1:1 to the control (standard recruitment pack only) or intervention group (standard recruitment pack including modified consent form with a qr code). Results: In total, 27 out of 40 patients (age: mean 63.0, SD 14.8 years;45% female) responded to the consent form. A lower proportion of the qr code group (60%) responded (odd ratio [OR] 0.57, 95% CI 0.14-2.37;P=.44), compared to 75% of the standard recruitment group. However, a higher proportion of the qr group (35%) consented (OR 1.84, 95% CI 0.41-8.29;P=.43), compared to the standard recruitment group (20%). A lower proportion of the qr group (25%) declined (OR 0.34, 95% CI 0.09-1.38;P=.13) relative to the standard recruitment group (55%). The mean response time of the qr code group was 16 days (rate ratio [RR] 0.79, 95% CI 0.47-1.35;P=.39) compared to 19 days for the standard recruitment group. None of the age-adjusted Conclusions: This underpow

关键词： qr code qualitative research cancer randomized controlled trial RCT patient recruitment consent forms response rates

来源：评论

学校读者我要写书评

暂无评论

Review and concepts on how construction and facilities management can utilize barcode and qr code technology to access documents onsite

引用

Procedia Computer Science 2025年 253卷 1313-1322页

作者： Robert Lopez Alexander Rose Lecturer Construction Management Discipline School of Design and the Built Environment (DBE) Curtin University GPO Box U1987 Perth 6845 Australia Innovation Central Perth (ICP) Intern Computing Discipline School of Electrical Engineering Computing and Mathematical Sciences (EECMS) Curtin University GPO Box U1987 Perth 6845 Australia

This research aimed to determine the applicability of utilizing barcode and qr code technology to improve construction and facilities management efficiency. The significance is that this technology can automate onsite access of construction practitioners and facilities management to documents. An investigation of the technological maturity to achieve this is presented, focusing on what their technology companies are capable of providing. Comparative analyses of two relevant technology provider companies and the four innovative concepts they proposed were performed. Their business models, functions, capabilities and devices were compared. Each technology provider company is capable of offering a greater diversity of products and services than their involvement in proposing these concepts. This research is timely due to limited previous studies on the utilization of this technology to automate construction and facilities management. Fundamental to their implementation feasibility are issues of company policies, quality, cost, customer service, terms and conditions, capabilities, use, storage, security, building information modeling, other devices or operating systems.

关键词： Barcode qr code Documentation Construction Management Facilities Management

来源：评论

学校读者我要写书评

暂无评论

qr code recognition based on HOG and multiclass SVM classifier

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第17期83卷 49993-50022页

作者： Tribak, Hicham Gaou, Mehdi Gaou, Salma Zaz, Youssef Ibn Zohr Univ Polydisciplinary Fac Ouarzazate Lab Phys Energy & Informat Proc Ouarzazate Morocco Abdelmalek Essaadi Univ Fac Sci Tetouan Tetouan Morocco

qr codes are often placed on complex backgrounds and under unstable illumination conditions, which in fact renders their localization and decoding quite challenging. In this paper, we propose a robust system devised to ensure two main tasks: firstly, extracting qr codes from captured images regardless of their quality. Secondly, enhance the extracted qr codes textures so that they can be decoded correctly. A qr code is principally localized through three finder patterns (FPs), which are placed in its three corners, as well as a set of alignment patterns (APs). FP and AP are characterized by specific textures (alternative black and white pixel sequences), defined respectively by the following ratios: 1:1:3:1:1 and 1:1:1:1:1. The proposed system starts by segmenting the captured image using an achromatic filter. This is followed by horizontal and vertical scans, aiming at extracting the valid horizontal and vertical segments satisfying the aforementioned ratios. Afterwards, the valid segment intersection is computed to localize candidate areas containing FPs and APs. The rough extracted patterns are filtered based on Multiclass Support Vector Machine classifier combined with the histogram of Oriented Gradients. The retained patterns are then transmitted to a pattern closeness measurement algorithm to conveniently localize qr code positions. In order to evaluate the robustness and weakness of the proposed approach, a comparative study has been carried out. In this study, we compared our approach against the most relevant competitive qr code extractors, such as Zxing, Zbar, Quirc, Leadtools and Dynamsoft. Our algorithm outperforms the evoked extractors with a precision rate of 97,3% and 96% under motion blur and JPEG compression respectively. Furthermore, the execution time analysis proved that our algorithm is not computationally expensive with a maximum running time of 1092 ms at a high resolution image and high number of qr codes per image..

关键词： qr code Pattern recognition Histogram of Oriented Gradients Multiclass SVM classifier Morphological filter Perspective rectification

来源：评论

学校读者我要写书评

暂无评论

qr code based blind digital image watermarking with attack detection code

引用

AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS 2015年第7期69卷 1074-1084页

作者： Thulasidharan, Pillai Praveen Nair, Madhu S. Univ Kerala Dept Comp Sci Thiruvananthapuram 695581 Kerala India

A qr code based blind digital image watermarking technique with an attack detection feature is described here. The technique describes a key based framework to incorporate image, server port address or website address as watermark data;which increases the extended usability of the embedded data and the adaptability of the verification application. The watermarking problem is formulated as a signal communication problem with watermark data representation, embedding of watermark and attack detection as a source encoding, channel encoding and attenuation detection problems respectively. The mathematical aspects of the respective signal processing problems are extended to digital image watermarking with sufficient background support. The use of qr code ensures extended usability, while the application specific watermark data achieves adaptability of the verification application. The qr code is embedded into the attack resistant HH component of 1st level DWT domain of the cover image and to detect malicious interference by an attacker, a unique image registry code generated from the high frequency structural components of the stego-image is used. The key based approach and the attack resistant embedding domain makes this method robust against visually invariant attacks. The testing results show the compliance of the method with all the proposed aspects. (C) 2015 Elsevier GmbH. All rights reserved.

关键词： Blind watermarking qr code Data hiding Distortion detection Image registry code

来源：评论

学校读者我要写书评

暂无评论

qr code arbitrary style transfer algorithm based on style matching layer

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第13期83卷 38505页

作者： Li, Hai-Sheng Chen, Jingyin Huang, Huafeng Guangxi Normal Univ Sch Elect & Informat Engn Guilin 541004 Guangxi Peoples R China

A single style transfer model can realize the Quick Response (qr) code beautification task. However, the number of styles in the single-style transfer model is limited, and the training must be carried out in advance to expand to new styles, which requires a lot of training time and memory. Therefore, the flexibility of the model needs to be further improved. The current mainstream arbitrary style transfer algorithm solves the flexibility problem and can complete the transfer task of any style after one training. Unfortunately, the existing arbitrary style transfer algorithms have issues such as heavy computational burden, distorted content, and blurred details, which are unsuitable for qr code beautification tasks. This paper proposes an arbitrary style conversion algorithm based on a style-matching layer to solve the above problems. Our algorithm obtains the style information using a small convolutional neural network and then transmits the second-order statistics of style images through a linear matrix multiplication to achieve arbitrary style transfer. Simulation results show that the proposed algorithm can efficiently complete the general style transfer task and has a higher visual quality and testing speed than the existing arbitrary style transfer models. Meanwhile, the algorithm can flexibly combine multi-level style features to complete the qr code style beautification task. Furthermore, there is a great affinity between the image generated by the proposed algorithm and the original image without distorted content and fuzzy details. Therefore, the generated style beautified qr code has high visual quality and recognition.

关键词： qr code Image style transfer Deep learning Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

qr code Authentication with Embedded Message Authentication code

引用

MOBILE NETWORKS & APPLICATIONS 2017年第3期22卷 383-394页

作者： Chen, Changsheng Shenzhen Univ Coll Informat Engn Shenzhen Peoples R China Shenzhen Univ Shenzhen Key Lab Media Secur Shenzhen Peoples R China

Quick Response (qr) code is widely used nowadays but its authenticity is an open issue. Attackers can easily replace the original barcode by a modified one which is generated through the standard encoder. This paper proposes to embed the authentication data such as message authentication code and cryptographic signature for qr code authentication. The scheme utilizes the redundancy of the error correction codewords to store the authentication data while still maintaining the default error correction capability. The stego barcode can be decoded by common users with a standard barcode decoder. The embedded data can be extracted with the knowledge of the barcode structure and the embedding process. The authenticity of the qr codes can then be verified off-line by the authorized user as and when needed. In our experiment, 100 % of the embedded data and encoded information can be retrieved correctly in the decodable barcodes with the off-the-shelf cameras. Security analysis shows that the proposed scheme is secure against attacks in tampering the barcode content. Compared with the existing data hiding scheme, the proposed method has much higher embedding capacity under the same error correction level.

关键词： qr code Data embedding Message authentication code Error correction code Authentication

来源：评论

学校读者我要写书评

暂无评论

qr code-based non-linear image encryption using Shearlet transform and spiral phase transform

引用

JOURNAL OF MODERN OPTICS 2018年第3期65卷 321-330页

作者： Kumar, Ravi Bhaduri, Basanta Hennelly, Bryan Indian Sch Mines Dhanbad Indian Inst Technol Dept Appl Phys Opt Imaging & Image Proc Lab Dhanbad Bihar India Maynooth Univ Dept Elect Engn Maynooth Ireland Maynooth Univ Dept Comp Sci Maynooth Ireland Maynooth Univ Hamilton Inst Maynooth Ireland

In this paper, we propose a new quick response (qr) code-based non-linear technique for image encryption using Shearlet transform (ST) and spiral phase transform. The input image is first converted into a qr code and then scrambled using the Arnold transform. The scrambled image is then decomposed into five coefficients using the ST and the first Shearlet coefficient, C-1 is interchanged with a security key before performing the inverse ST. The output after inverse ST is then modulated with a random phase mask and further spiral phase transformed to get the final encrypted image. The first coefficient, C-1 is used as a private key for decryption. The sensitivity of the security keys is analysed in terms of correlation coefficient and peak signal-to noise ratio. The robustness of the scheme is also checked against various attacks such as noise, occlusion and special attacks. Numerical simulation results are shown in support of the proposed technique and an optoelectronic set-up for encryption is also proposed.

关键词： Shearlet transform spiral phase transform image encryption qr code Arnold transform

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：