Key Laboratory of Aerospace Information Security and Trusted Computing,Ministry of Education,School of Cyber Science and Engineering,Wuhan University,Wuhan 430072,Hubei,China
With the widespread adoption of smart devices, capacitive touchscreens (“capacitive screens”) have become increasingly popular. However, further development is constrained by its relatively low imaging resolution due to the hardware design and imaging principles. To overcome this limitation, we propose a super-resolution imaging method that reconstructs high-resolution capacitive images by aggregating multiple frames captured during the movement of conductive objects. The proposed super-resolution algorithm comprises three essentials procedures: preprocessing, image reconstruction, and visual optimization. In the preprocessing stage, YOLOv8n and Nano tracker are employed respectively for object detection and object tracking, enabling background noise removal, thus resulting in clean low-resolution capacitive image sequences. During the image reconstruction phase, each frame undergoes Lanczos upsampling, alignment, and merging, ensuring the preservation of image detail and fidelity. Finally, the visual optimization stage introduces a capacitive image deblurring algorithm, which, as validated by experiments, exhibits the best deblurring effect, effectively enhancing image clarity and edge details. Extensive experiments are conducted on a large dataset to evaluate the effectiveness and necessity of the super-resolution algorithm proposed in this paper. The experimental results demonstrate significant advantages of the proposed algorithm in terms of imaging performance, and effectively improve the image resolution and visual quality of capacitive images.
本文可选用的目标检测模型包括YOLOv5-small模型(以下简称YOLOv5s)和YOLOv8-nano模型(以下简称YOLOv8n)。可选用的目标跟踪算法包括基于滤波算法的跟踪器,如内核相关滤波器(Kernelized Correlation Filter, KCF)跟踪算法[16]、信道和空间可靠性跟踪(Channel and Spatial Reliability Tracking, CSRT)算法[17];以及基于孪生神经网络算法的跟踪器,如DaSiamRPN(Deeper and wider Siamese networks with Region Proposal Network)跟踪算法[18]和在此基础上进行优化的Nano跟踪器(https://github.com/HonglinChu/SiamTrackers/tree/master/NanoTrack)。
HOLZC, BAUDISCHP. Understanding touch[C]//Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. New York: ACM, 2011: 2501-2510. DOI: 10.1145/1978942.1979308 .
[2]
JIANGY, JIX Y, WANGK, et al. WIGHT: wired ghost touch attack on capacitive touchscreens[C]//2022 IEEE Symposium on Security and Privacy (SP). New York: IEEE Press, 2022: 984-1001. DOI: 10.1109/SP46214.2022.9833740 .
[3]
RUSUM, MAYERS. Deep learning super-resolution network facilitating fiducial tangibles on capacitive touchscreens[C]//Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2023: 1-16. DOI: 10.1145/3544548.3580987 .
[4]
SHANH Q, ZHANGB Y, ZHANZ H, et al. Invisible finger: Practical electromagnetic interference attack on touchscreen-based electronic devices[C]//2022 IEEE Symposium on Security and Privacy (SP). New York: IEEE Press, 2022: 1246-1262. DOI: 10.1109/SP46214.2022.9833718 .
[5]
HOLZC, BUTHPITIYAS, KNAUSTM. Bodyprint: Biometric user identification on mobile devices using the capacitive touchscreen to scan body parts[C]//Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. New York: ACM, 2015: 3011-3014. DOI: 10.1145/2702123.2702518 .
[6]
LEH V, KOSCHT, BADERP, et al. PalmTouch: Using the palm as an additional input modality on commodity smartphones[C]//Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2018: 1-13. DOI: 10.1145/3173574.3173934 .
[7]
MAYERS, XUX Y, HARRISONC. Super-resolution capacitive touchscreens[C]//Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2021: 1-10. DOI: 10.1145/3411764.3445703 .
[8]
XIAOR, HUDSONS, HARRISONC. CapCam: Enabling rapid, ad-hoc, position-tracked interactions between devices[C]//Proceedings of the 2016 ACM International Conference on Interactive Surfaces and Spaces. New York: ACM, 2016: 169-178. DOI: 10.1145/2992154.2992182 .
[9]
EVANGELIDISG D, PSARAKISE Z. Parametric image alignment using enhanced correlation coefficient maximization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(10): 1858-1865. DOI: 10.1109/TPAMI.2008.113 .
XUX Y, MAY R, SUNW X. Towards real scene super-resolution with raw images[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE Press, 2020: 1723-1731. DOI: 10.1109/CVPR.2019.00182 .
[12]
DONGC, LOYC C, HEK M, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. DOI: 10.1109/TPAMI.2015.2439281 .
[13]
KALTENBRUNNERM, BENCINAR. reacTIVision: A computer-vision framework for table-based tangible interaction[C]//Proceedings of the 1st International Conference on Tangible and Embedded Interaction. New York: ACM, 2007: 69-74. DOI: 10.1145/1226969.1226983 .
[14]
XUL, ZHENGS C, JIAJ Y. Unnatural L0 sparse representation for natural image deblurring[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2013: 1107-1114. DOI: 10.1109/CVPR.2013.147 .
[15]
BOCHKOVSKIYA, WANGC Y, LIAOH Y M. YOLOv4: Optimal speed and accuracy of object detection[EB/OL]. 2020: arXiv: 2004.10934. DOI: 10.48550/arXiv.2004.10934 .
[16]
HENRIQUESJ F, CASEIROR, MARTINSP, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596. DOI: 10.1109/TPAMI.2014.2345390 .
[17]
LUKEŽICA, VOJÍRT, ZAJCL C, et al. Discriminative correlation filter with channel and spatial reliability[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE Press, 2017: 4847-4856. DOI: 10.1109/CVPR.2017.515 .
[18]
ZHUZ, WANGQ, LIB, et al. Distractor-aware Siamese networks for visual object tracking[C]//European Conference on Computer Vision. Cham: Springer, 2018: 103-119.10.1007/978-3-030-01240-3_7. DOI: 10.1007/978-3-030-01240-3_7 .
[19]
SHANQ, JIAJ Y, AGARWALAA. High-quality motion deblurring from a single image[J]. ACM Transactions on Graphics, 27(3): 1-10. DOI: 10.1145/1360612.1360672 .
[20]
KUPYNO, BUDZANV, MYKHAILYCHM, et al. DeblurGAN: blind motion deblurring using conditional adversarial networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2018: 8183-8192. DOI: 10.1109/CVPR.2018.00854 .
[21]
KUPYNO, MARTYNIUKT, WUJ R, et al. DeblurGAN-v2: Deblurring (orders-of-magnitude) faster and better[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). New York: IEEE Press, 2020: 8877-8886. DOI: 10.1109/ICCV.2019.00897 .
[22]
TUZ Z, TALEBIH, ZHANGH, et al. MAXIM: multi-axis MLP for image processing[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE Press, 2022: 5759-5770. DOI: 10.1109/CVPR52688.2022.00568 .
[23]
MANSOURY, HECKELR. Zero-shot Noise2Noise: Efficient image denoising without any data[EB/OL]. 2023: arXiv: 2303.11253. DOI: 10.1109/cvpr52729.2023.01347 .
[24]
RAYLEIGH. XXXI. Investigations in optics, with special reference to the spectroscope[J]. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, 1879, 8(49): 261-274. DOI: 10.1080/14786447908639684 .
[25]
RADIOA. Introduction to radio interferometry [EB/OL]. [2020-02-05].