Real‐time recovery and recognition of motion blurry QR code image based on fractional order deblurring method

Yu, XiaoYuan; Xie, Wei

doi:10.1049/iet-ipr.2018.5792

Cited by 7 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results: (1) the result of the sequential action proposal directly affects the result of the sequential action detection; (2) the SVR algorithm can significantly improve the effect of sequential action detection under different tIoU requirements [24,25].…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Action Recognition, Tracking, and Optimization Analysis of Training Process Based on SVR Model and Multimedia Technology

Zhong

2022

Advances in Multimedia

View full text Add to dashboard Cite

In order to explore the action recognition, tracking, and optimization analysis of the training process based on the SVR model and multimedia technology, the author proposes based on the radial basis function model, researching a new surrogate model technology-support vector regression (SVR). We first introduce the basic principles of SVR, select the parameters of SVR, and then elaborate the basic steps of SVR modeling. Then, we design and optimize application examples through numerical example multimedia technology; the validity of the support vector regression method is verified. Experimental results: the comparison of SVR1 and SVR2 shows that the utilization of multiscale timing feature maps should occur after tem (SVR2) rather than being directly fused in the feature dimension (SVR1), mainly because small-scale information affects the resolution of large-scale information; on data sets such as ActivityNet, in order to verify the effectiveness of SVR and DR-Dvc algorithms, the performance of the proposed algorithm and the baseline before improvement and the current mainstream algorithm are respectively compared. Experimental results show the proposed algorithm has a significant performance improvement compared to before the improvement; at the same time, it is better than most current mainstream algorithms, which proves the feasibility and effectiveness of the algorithm. Describing the introduction of regression can effectively improve the performance of sequential action proposals and event description algorithms, and compared with the current mainstream methods, it has certain performance advantages.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Action Recognition, Tracking, and Optimization Analysis of Training Process Based on SVR Model and Multimedia Technology

Zhong

2022

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…Pu et al [21] proposed a Convolutional Neural Network-based framework for image pre-processing on QR codes identification using ZBar to recover blurry QR codes caused by out-of-focus blur and motion blur. Yu [22] proposed a method to do image deblurring using fractional differential order. Both Pu et al [21] and Yu [23] were able to reach the QR codes recognition rate >90%.…”

Section: Introductionmentioning

confidence: 99%

Moving Quick Response Codes Identification: System Performance Analysis and Maximization by Optimization of Illuminance and Exposure Time

Sunarko¹,

Faridah²,

Arif³

et al. 2022

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

We studied the relationship of Quick Response (QR) code identification system performances with illuminance on the QR code, exposure time of the camera, and relative moving speed. We studied the root causes of low identification performance problems on moving QR code as well. A physical experiment method study on a minimal working example of a real-time moving QR codes identification system with ZBar QR codes identification algorithm has done, and then the results were quantitatively and qualitatively analyzed. The values of illuminance on the QR code, exposure time of the camera, and relative moving speed used in the experiments were 140 lux -640 lux, 0.7 ms -22.2 ms, and 0 m/s -2.5 m/s, respectively. Our data boundaries of the experiment results regarding exposure and motion blur (mediator variables) were respectively 0.108 lux•s -12.476 lux•s and 0.0 pixel -30.4 pixel. We identified physical phenomena in imaging, exposure and motion blur, could make the QR code image too dark/too bright and motion blurred.Such phenomena could make the QR code hard to identify and being the root cause of the problems. Our quantitative study proved that identification system performance is affected by illuminance, exposure time, and relative moving speed. Finally, we proposed a novel solution to overcome the problems by using a numerical method to compute the optimal illuminance on the QR code and the camera's exposure time for the given relative moving speed of the system.

show abstract

“…Van Gennip et al [10] proposed a solution on the deblurred QR code image, which could heighten the accuracy of decoding and accelerate the extraction of QR code. Yu and Xie [11] proposed a real‐time recovery and recognition of motion blurry QR code image based on the fractional‐order deblurring method. Ahn et al [12] used the cloud‐based pre‐generated image to match schemes to tackle the issue.…”

Section: Introductionmentioning

confidence: 99%

Recognition of distorted QR codes with one missing position detection pattern

Huang

Wang

et al. 2020

IET image process

View full text Add to dashboard Cite

Real‐time recovery and recognition of motion blurry QR code image based on fractional order deblurring method

Cited by 7 publications

References 22 publications

Action Recognition, Tracking, and Optimization Analysis of Training Process Based on SVR Model and Multimedia Technology

Action Recognition, Tracking, and Optimization Analysis of Training Process Based on SVR Model and Multimedia Technology

Moving Quick Response Codes Identification: System Performance Analysis and Maximization by Optimization of Illuminance and Exposure Time

Recognition of distorted QR codes with one missing position detection pattern

Contact Info

Product

Resources

About