山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (5): 111-121.doi: 10.6040/j.issn.1672-3961.0.2023.260
• 机器学习与数据挖掘 • 上一篇
方世超1,滕旭阳1*,王子南2,陈晗1,仇兆炀1,毕美华1
FANG Shichao1, TENG Xuyang1*, WANG Zinan2, CHEN Han1, QIU Zhaoyang1, BI Meihua1
摘要： 针对现有图像保护技术中全图加密增加计算成本和区域遮挡无法判定多目标等问题,提出基于自适应掩码和生成式修复的图像保护框架。该框架采用Score-CAM(class activation mapping)技术自适应判别图像的核心区域,准确生成多目标核心区域掩膜;采用遮挡方法保护图像隐私来降低计算开销;引入区域感知的CAM损失函数,确保修复图像重点区域的一致性。将有遮挡的图像送入修复网络进行训练,对训练好的网络参数进行椭圆加密;在发送阶段将掩码图像和密钥分开发送,接收端通过密钥解密,Shift-Net网络载入参数对掩码图像进行准确修复。在ImageNet数据集中的试验表明,CAM损失函数的修复模型使得生成图像的结构相似性指标提高了0.2%、学习感知图像块相似度降低了0.2%。本研究在接收端自适应对图像重点区域进行掩码,使得识别模型失效进而保护图像隐私。
中图分类号:
| [1] BRRAHIM A H, PACHA A A, SAID N H. Image encryption based on compressive sensing and chaos systems[J]. Optics and Laser Technology, 2020, 132:106489-106499. [2] 陈炜, 郭媛, 敬世伟. 基于深度学习压缩感知与复合混沌系统的通用图像加密算法[J]. 物理学报, 2020, 69(24):99-111. CHEN Wei, GUO Yuan, JING Shiwei. General image encryption algorithm based on deep learning compressed sensing and compound chaotic system[J]. Acta Phys Sinica, 2020, 69(24):99-111. [3] NI Renjie, WANG Fan, WANG Jun, et al. Multi-image encryption based on compressed sensing and deep learning in optical gyrator domain[J]. IEEE Photonics Journal, 2021, 13(3):1-16. [4] CHAI Xiuli, TIAN Ye, GAN Zhihua, et al. A robust compressed sensing image encryption algorithm based on GAN and CNN[J]. Journal of Modern Optics, 2022, 69(2):103-120. [5] LIU Jinqiang, LIU Yining, CUI Lei, et al. MSAI: masking sensitive area of image on IoT cameras[J]. Journal of Internet Technology. 2021, 22(7):1553-1562. [6] PATHAK D, KRAHENBUHL P, DONAHUE J, et al. Context encoders:feature learning by inpainting[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA:IEEE, 2016:2536-2544. [7] IIZUKA S, SIMO-SERRA E, ISHIKAWA H. Globally and locally consistent image completion[J]. ACM Transactions on Graphics(ToG), 2017, 36(4):1-14. [8] YANG Chao, LU Xin, LIN Zhe, et al. High-resolution image inpainting using multi-scale neural patch synthesis[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA:IEEE, 2017:6721-6729. [9] 曹志义, 牛少彰, 张继威. 基于生成对抗网络的遮挡图像修复算法[J]. 北京邮电大学学报, 2018, 41(3):81-86. CAO Zhiyi, NIU Shaozhang, ZHANG Jiwei. Masked image inpainting algorithm based on generative adversarial Nets[J]. Journal of Beijing University of Posts and Telecommunications, 2018, 41(3):81-86. [10] YAN Zhaoyi, LI Xiaoming, LI Mu, et al. Shift-net:Image inpainting via deep feature rearrangement[C] //Proceedings of the European Conference on Computer Vision(ECCV). Munich, Germany:Springer, 2018:1-17. [11] LIU Guilin, FITSUM A, KKEVIN J, et al. Image inpainting for irregular holes using partial convolutions[C] //Proceedings of the European Conference on Computer Vision(ECCV). Munich, Germany:Springer, 2018:85-100. [12] XIE Chaochao, LIU Shaohui, LI Chao, et al. Image inpainting with learnable bidirectional attention maps[C] //Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision(ICCV). Seoul, Korea:IEEE, 2019:8858-8867. [13] LIU Hongyu, JIANG Bin, XIAO Yi, et al. Coherent semantic attention for image inpainting[C] //Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision(ICCV). Seoul, Korea:IEEE, 2019:4170-4179. [14] WANG Haofan, WANG Zifan, DU Mengnan. Score-CAM:score-weighted visual explanations for convolutional neural networks[C] //Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). Seattle, USA:IEEE, 2020:111-119. [15] ZHAO Lulu, SHEN Ling, HONG Richang. Survey on image inpainting research progress[J]. Computer Science, 2021, 48(3):14-26. [16] ROJAS D J B, FERNANDES B J T, FERNANDES S M M. A review on image inpainting techniques and datasets[C] //Proceedings of the 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images(SIBGRAPI), Porto de Galinhas, Brazil:IEEE, 2020:240-247. [17] AZHAR S, AZAM N, HAYAT U. Text encryption using pell sequence and elliptic curves with provable security[J]. Computers, Materials & Continua, 2022, 71(3):4971-4988. [18] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C] // Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, USA:IEEE, 2016:770-778. [19] JOHNSON J, ALAHI A, LI F F. Perceptual losses for real-time style transfer and super-resolution[C] // Proceedings of the 2016 IEEE Computer Vision-ECCV. Amsterdam, Netherlands:Springer, 2016:694-711. [20] ABOAH A, WANG B, BAGCI U, et al. Real-time multi-class helmet violation detection using few-shot data sampling technique and yolov8[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, Canada:IEEE, 2023:5349-5357. [21] REN Shaoqing, HE Kaiming, GIRSHICK R. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149. [22] ZHANG R, ISOLA P, EFROS A A, et al. The unreasonable effectiveness of deep features as a perceptual metric[C] //Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City, USA:IEEE, 2018:586-595. |
| [1] | 廖南星,周世斌,张国鹏,程德强. 基于类激活映射-注意力机制的图像描述方法[J]. 山东大学学报 (工学版), 2020, 50(4): 28-34. |
|
||
