[1]林孙旗,徐家梦,郑瑜杰,等.面向掌纹掌静脉识别网络轻量化的非对称双模态融合方法[J].智能系统学报,2024,19(5):1190-1198.[doi:10.11992/tis.202212031]
LIN Sunqi,XU Jiameng,ZHENG Yujie,et al.An asymmetric bimodal fusion method for lightweight palm print and palm vein recognition network[J].CAAI Transactions on Intelligent Systems,2024,19(5):1190-1198.[doi:10.11992/tis.202212031]
点击复制
LIN Sunqi,XU Jiameng,ZHENG Yujie,et al.An asymmetric bimodal fusion method for lightweight palm print and palm vein recognition network[J].CAAI Transactions on Intelligent Systems,2024,19(5):1190-1198.[doi:10.11992/tis.202212031]
面向掌纹掌静脉识别网络轻量化的非对称双模态融合方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第5期
页码:
1190-1198
栏目:
学术论文—机器感知与模式识别
出版日期:
2024-09-05
- Title:
- An asymmetric bimodal fusion method for lightweight palm print and palm vein recognition network
- Keywords:
- deep learning; biometrics; palm print and vein recognition; multimodal network; knowledge distillation; model compression; convolutional neural network; class activation map
- 分类号:
- TP30
- 文献标志码:
- 2024-08-28
- 摘要:
- 深度学习已在掌纹掌静脉领域广泛应用，但随着任务使用场景的不断微型化、终端化，现有的深度学习模型往往难以在算力匮乏、内存有限的边缘设备上顺利部署。本文基于知识蒸馏方法提出了轻量化的掌纹掌静脉识别网络。根据模态特征提取复杂程度，为掌纹与掌静脉模态分别选用不同的网络深度。在常规知识蒸馏方法中引入新设计的模态特征损失函数，强化教师模型对各模态特征提取的指导作用。实验结果表明，该方法有效协调了模型大小与性能，为边缘计算环境下的生物特征识别技术提供了一种有效的解决方案。
- Abstract:
- Deep learning has been widely used in palm print and palm vein recognition. However, with the continuous miniaturization and terminalization of task usage scenarios, it is often challenging to deploy current deep-learning models successfully on edge devices that suffer from limited computational power and memory constraints. In this study, we propose a lightweight palm print and palm vein recognition network based on knowledge distillation. First, we select different network depths for the palm print and palm vein modalities according to the complexity of their feature extraction. We introduce a novel modality feature loss function into the traditional knowledge distillation method to enhance the guiding role of the teacher model in the feature extraction of each modality. The experimental results demonstrate that this method effectively balances model size with performance and offers a viable solution for biometric recognition technologies within an edge computing environment.
- 参考文献/References:
-
[1] 李倩颖, 阮秋琦. 分辨率LBP的掌纹特征提取[J]. 智能系统学报, 2010, 5(6): 482-486.
LI Qianying, RUAN Qiuqi. Palmprint feature extraction based on multiresolution LBP[J]. CAAI transactions on intelligent systems, 2010, 5(6): 482-486.
[2] 孙波. 基于深度学习的掌静脉识别算法研究与识别系统[D]. 桂林: 桂林电子科技大学, 2022.
SUN Bo. Research on palmar vein recognition algorithm and recognition system based on deep learning[D]. Guilin: Guilin University of Electronic Technology, 2022.
[3] ZHONG Dexing, YANG Yuan, DU Xuefeng. Palmprint recognition using Siamese network[C]//Chinese Conference on Biometric Recognition. Cham: Springer, 2018: 48-55.
[4] ZHAO Shuping, ZHANG B, PHILIP CHEN C L. Joint deep convolutional feature representation for hyperspectral palmprint recognition[J]. Information sciences, 2019, 489: 167-181.
[5] AHMED M A, ROUSHDY M, SALEM A B M. Multi- modal technique for human authentication using fusion of palm and dorsal hand veins[C]//New Approaches for Multidimensional Signal Processing. Singapore: Springer, 2022: 63-78.
[6] LOU Jiashu, ZOU Jie, WANG Baohua. Palm vein reco- gnition via multi-task loss function and attention layer[EB/OL]. (2022-11-11)[2022-12-31]. http://arxiv.org/abs/2211.05970.
[7] WANG Weiyao, TRAN D, FEISZLI M. What makes training multi-modal classification networks hard? [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 12692-12702.
[8] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[9] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//European Conference on Computer Vision. Cham: Springer, 2018: 3-19.
[10] LI Xiang, WANG Wenhai, HU Xiaolin, et al. Selective kernel networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 510-519.
[11] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient- based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[12] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[13] DEVLIN J, CHANG Mingwei, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[EB/OL]. (2018-10-11)[2022-12-31]. https://arxiv.org/abs/1810.04805.
[14] BROWN T, MANN B, RYDER N, et al. Language models are few-shot learners[J]. Advances in neural information processing systems, 2020, 33: 1877-1901.
[15] HAN Song, MAO Huizi, DALLY W J. Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding[EB/OL]. (2015-10-01) [2022-12-31]. http://arxiv.org/abs/1510.00149.
[16] HE Yihui, ZHANG Xiangyu, SUN Jian. Channel pruning for accelerating very deep neural networks[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 1398-1406.
[17] CHENG Jian, WU Jiaxiang, LENG Cong, et al. Quantized CNN: a unified approach to accelerate and compress convolutional networks[J]. IEEE transactions on neural networks and learning systems, 2018, 29(10): 4730-4743.
[18] MERONE M, GRAZIOSI A, LAPADULA V, et al. A practical approach to the analysis and optimization of neural networks on embedded systems[J]. Sensors, 2022, 22(20): 7807-7822.
[19] 邵仁荣, 刘宇昂, 张伟, 等. 深度学习中知识蒸馏研究综述[J]. 计算机学报, 2022, 45(8): 1638-1673.
SHAO Renrong, LIU Yuang, ZHANG Wei, et al. A survey of knowledge distillation in deep learning[J]. Chinese journal of computers, 2022, 45(8): 1638-1673.
[20] 黄震华, 杨顺志, 林威, 等. 知识蒸馏研究综述[J]. 计算机学报, 2022, 45(3): 624-653.
HUANG Zhenhua, YANG Shunzhi, LIN Wei, et al. Knowledge distillation: a survey[J]. Chinese journal of computers, 2022, 45(3): 624-653.
[21] HINTON G, VINYALS O, DEAN J. Distilling the knowledge in a neural network[EB/OL]. (2015-03-09) [2022-12-31]. http://arxiv.org/abs/1503.02531.
[22] ROMERO A, BALLAS N, KAHOU S E, et al. FitNets: hints for thin deep nets[EB/OL]. (2014-12-19)[2022-12-31]. http://arxiv.org/abs/1412.6550.
[23] SUN Zhenan, TAN Tieniu, WANG Yunhong, et al. Ordinal palmprint represention for personal identification [represention read representation][C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 279-284.
[24] ZHANG Lin, CHENG Zaixi, SHEN Ying, et al. Palmprint and palmvein recognition based on DCNN and a new large-scale contactless palmvein dataset[J]. Symmetry, 2018, 10(4): 78-39.
[25] SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[J]. International journal of computer vision, 2020, 128(2): 336-359.
[26] 吴晓昱. 电子废弃物拆机塑料的近红外光谱识别[D]. 上海: 上海交通大学, 2020.
WU Xiaoyu. Identification of electronic waste dismantling plastics by near infrared spectroscopy[D]. Shanghai: Shanghai Jiao Tong University, 2020.
[27] ZHAO Shuping, ZHANG B. Joint constrained least-square regression with deep convolutional feature for palmprint recognition[J]. IEEE transactions on systems, man, and cybernetics: systems, 2022, 52(1): 511-522.
[28] HASSAN N F, ABDULRAZZAQ H I. Pose invariant palm vein identification system using convolutional neural network[J]. Baghdad science journal, 2018, 15(4): 503-510.
- 相似文献/References:
-
[1]颜廷秦,周昌雄.二维EMD分解提高PCA掌纹识别率[J].智能系统学报,2013,8(4):377.[doi:10.3969/j.issn.1673-4785.201211002]
YAN Tingqin,ZHOU Changxiong.The research of improving PCA recognition rate of palmprints with BEMD[J].CAAI Transactions on Intelligent Systems,2013,8():377.[doi:10.3969/j.issn.1673-4785.201211002]
[2]张媛媛,霍静,杨婉琪,等.深度信念网络的二代身份证异构人脸核实算法[J].智能系统学报,2015,10(2):193.[doi:10.3969/j.issn.1673-4785.201405060]
ZHANG Yuanyuan,HUO Jing,YANG Wanqi,et al.A deep belief network-based heterogeneous face verification method for the second-generation identity card[J].CAAI Transactions on Intelligent Systems,2015,10():193.[doi:10.3969/j.issn.1673-4785.201405060]
[3]丁科,谭营.GPU通用计算及其在计算智能领域的应用[J].智能系统学报,2015,10(1):1.[doi:10.3969/j.issn.1673-4785.201403072]
DING Ke,TAN Ying.A review on general purpose computing on GPUs and its applications in computational intelligence[J].CAAI Transactions on Intelligent Systems,2015,10():1.[doi:10.3969/j.issn.1673-4785.201403072]
[4]陈阳,覃鸿,李卫军,等.仿生模式识别技术研究与应用进展[J].智能系统学报,2016,11(1):1.[doi:10.11992/tis.201506011]
CHEN Yang,QIN Hong,LI Weijun,et al.Progress in research and application of biomimetic pattern recognition technology[J].CAAI Transactions on Intelligent Systems,2016,11():1.[doi:10.11992/tis.201506011]
[5]刘帅师,程曦,郭文燕,等.深度学习方法研究新进展[J].智能系统学报,2016,11(5):567.[doi:10.11992/tis.201511028]
LIU Shuaishi,CHENG Xi,GUO Wenyan,et al.Progress report on new research in deep learning[J].CAAI Transactions on Intelligent Systems,2016,11():567.[doi:10.11992/tis.201511028]
[6]马世龙,乌尼日其其格,李小平.大数据与深度学习综述[J].智能系统学报,2016,11(6):728.[doi:10.11992/tis.201611021]
MA Shilong,WUNIRI Qiqige,LI Xiaoping.Deep learning with big data: state of the art and development[J].CAAI Transactions on Intelligent Systems,2016,11():728.[doi:10.11992/tis.201611021]
[7]王亚杰,邱虹坤,吴燕燕,等.计算机博弈的研究与发展[J].智能系统学报,2016,11(6):788.[doi:10.11992/tis.201609006]
WANG Yajie,QIU Hongkun,WU Yanyan,et al.Research and development of computer games[J].CAAI Transactions on Intelligent Systems,2016,11():788.[doi:10.11992/tis.201609006]
[8]黄心汉.A3I:21世纪科技之光[J].智能系统学报,2016,11(6):835.[doi:10.11992/tis.201605022]
HUANG Xinhan.A3I: the star of science and technology for the 21st century[J].CAAI Transactions on Intelligent Systems,2016,11():835.[doi:10.11992/tis.201605022]
[9]宋婉茹,赵晴晴,陈昌红,等.行人重识别研究综述[J].智能系统学报,2017,12(6):770.[doi:10.11992/tis.201706084]
SONG Wanru,ZHAO Qingqing,CHEN Changhong,et al.Survey on pedestrian re-identification research[J].CAAI Transactions on Intelligent Systems,2017,12():770.[doi:10.11992/tis.201706084]
[10]杨梦铎,栾咏红,刘文军,等.基于自编码器的特征迁移算法[J].智能系统学报,2017,12(6):894.[doi:10.11992/tis.201706037]
YANG Mengduo,LUAN Yonghong,LIU Wenjun,et al.Feature transfer algorithm based on an auto-encoder[J].CAAI Transactions on Intelligent Systems,2017,12():894.[doi:10.11992/tis.201706037]
[11]马晓,张番栋,封举富.基于深度学习特征的稀疏表示的人脸识别方法[J].智能系统学报,2016,11(3):279.[doi:10.11992/tis.201603026]
MA Xiao,ZHANG Fandong,FENG Jufu.Sparse representation via deep learning features based face recognition method[J].CAAI Transactions on Intelligent Systems,2016,11():279.[doi:10.11992/tis.201603026]
[12]王闪闪,巩长庆,秦华锋,等.基于深度学习的K近邻图迭代静脉识别算法研究[J].智能系统学报,2024,19(5):1149.[doi:10.11992/tis.202307009]
WANG Shanshan,GONG Changqing,QIN Huafeng,et al.Vein recognition algorithm combining K-nearest neighbor and graph iterative based on deep learning[J].CAAI Transactions on Intelligent Systems,2024,19():1149.[doi:10.11992/tis.202307009]
[13]金怡凡,王海涛,贾伟.使用掌纹线对基于深度学习的掌纹识别进行数据增强[J].智能系统学报,2024,19(5):1178.[doi:10.11992/tis.202308026]
JIN Yifan,WANG Haitao,JIA Wei.Using palmprint lines for data enhancement of palmprint recognition based on deep learning[J].CAAI Transactions on Intelligent Systems,2024,19():1178.[doi:10.11992/tis.202308026]
备注/Memo
收稿日期:2022-12-31。
基金项目:科技部科技创新2030 —“新一代人工智能”重大项目(2020AAA0107300)；宁波市自然科学基金项目(20221JCGY010068)；中国创新挑战赛(宁波)项目(2022T001).
作者简介:林孙旗，硕士研究生，主要研究方向为深度学习、模型轻量化。E-mail：sunqi1209@gmail.com;王翀，副教授，主要研究方向为模型轻量化，零样本、小样本目标检测，视频异常检测。主持国家自然科学基金项目1项。发表学术论文50余篇。E-mail：wangchong@nbu.edu.cn;王军，教授，博士生导师，主要研究方向为智能机器人与无人系统、生物特征识别、机器视觉。主持科技部科技创新2030—“新一代人工智能”重大项目，获得国家级教学科研奖1项、省部/学会级教学科研奖5项。获授权发明专利数十项，发表学术论文60余篇，出版专著教材6部。E-mail：jrobot@126.com。
通讯作者:王翀. E-mail：wangchong@nbu.edu.cn
更新日期/Last Update:
2024-09-05