Method of Small Sample Image Recognition Based on Prototype Network

doi:10.3969/j.issn.1006-2475.2020.03.020

Abstract

Abstract: In the current image recognition field, most of the classification or recognition methods are built on the basis of existing large amounts of data, which are put into training and classified through sampling analysis and feature extraction. However, in the real world, most target classification problems do not have a large amount of annotated data. In order to solve the problem of image recognition based on small data sets, this paper uses the data augmentation to enhance data sets, and uses multi-layer CNN to map the image into high-dimensional space, then gets prototypes of each class by using the prototype network. Finally, the test image can be classified according to the distance among prototype points and test image in the embedded space. Experimental results show that this method has high recognition accuracy under the condition of small data set, and also has good stability and strong robustness.

Key words: image recognition, small data set, CNN, prototype network, embedding space, data augmentation

CLC Number:

TP391.41

FAN Di, JU Zhi-yong. Method of Small Sample Image Recognition Based on Prototype Network[J]. Computer and Modernization, 2020, 0(03): 103-.

References

［1］ KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks［C］// Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012,1:1097-1105.
［2］段萌,王功鹏,牛常勇. 基于卷积神经网络的小样本图像识别方法［J］. 计算机工程与设计, 2018,39(1):224-229.
［3］ ABDEL-HAMID O, MOHAMED A R, JIANG H, et al. Convolutional neural networks for speech recognition［J］. IEEE ACM Transactions on Audio Speech & Language Processing, 2014,22(10):1533-1545.
［4］ GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］// IEEE Conference on Computer Vision & Pattern Recognition. 2014:580-587.
［5］ BOSE S, PAL A, SAHARAY R, et al. Generalized quadratic discriminant analysis［J］. Pattern Recognition, 2015,48(8):2676-2684.
［6］张海波,董槐林,龙飞,等. 基于BP神经网络的图像识别研究［J］. 计算机与现代化, 2008(5):17-19.
［7］ SHARMA A, PALIWAL K K. Linear discriminant analysis for the small sample size problem: An overview［J］. International Journal of Machine Learning & Cybernetics, 2015,6(3):443-454.
［8］李刚,高政. 人脸自动识别方法综述［J］. 计算机应用研究, 2003,20(8):4-9.
［9］宋晖,薛云,张良均. 基于SVM分类问题的核函数选择仿真研究［J］. 计算机与现代化, 2011(8):133-136.
［10］RADENOVIC F, TOLIAS G, CHUM O. Fine-tuning CNN image retrieval with no human annotation［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017,47(1):1655-1668.
［11］MONTI F, BOSCAINI D, MASCI J, et al. Geometric deep learning on graphs and manifolds using mixture model CNNs［C］// IEEE Conference on Computer Vision & Pattern Recognition. 2017:5425-5434.
［12］〖JP3〗VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning［J］. Advances in Neural Information Processing Systems, 2016,29(9):3630-3638.
［13］MENSINK T, VERBEEK J, PERRONNIN F, et al. Distance-based image classification: Generalizing to new classes at near-zero cost［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013,35(11):2624-2637.
［14］RAZAVIAN A S, AZIZPOUR H, SULLIVAN J, et al. CNN features off-the-shelf: An astounding baseline for recognition［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2014:806-813.
［15］RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge［J］. International Journal of Computer Vision, 2015,115(3):211-252.
［16］SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions［C］// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2015:1-9.
［17］CUI X D, GOEL V, KINGSBURY B. Data augmentation for deep neural network acoustic modeling［J］. IEEE-ACM Transactions on Audio Speech & Language Processing, 2015,23(9):5582-5586.
［18］DIGGAVI S N, CALDERBANK A R, DUSAD S, et al. Diversity-embedded space-time codes［J］. IEEE Transactions on Information Theory, 2008,54(1):33-50.
［19］WEINBERGER K Q, SAUL L K. Distance metric learning for large margin nearest neighbor classification［J］. Journal of Machine Learning Research, 2009,10:207-244.
［20］HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification［C］// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2015:1026-1034.
［21］SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: A simple way to prevent neural networks from overfitting［J］. Journal of Machine Learning Research, 2014,15:1929-1958.
［22］CHILIMBI T, SUZUE Y, APACIBLE J, et al.Project Adam: Building an efficient and scalable deep learning training system［C］// Usenix Conference on Operating Systems Design & Implementation. 2014:571-582.

[1]	HUANG Shanshan1, WU Wei2, XU Yuqing1, WEI Jie1. Pipelines in Drawings Detection Method Based on Improved Mask R-CNN and LSD [J]. Computer and Modernization, 2024, 0(10): 42-48.
[2]	FU Lingli, QIU Yu, ZHANG Xinchen. Retinal Vessel Segmentation Based on Improved U-Net with Multi-feature Fusion [J]. Computer and Modernization, 2024, 0(06): 76-82.
[3]	ZHANG Gao-yi1, XU Yang1, 2, CAO Bin1, 2, SHI Jin1. Global Cross-layer Interaction Networks Learning Fine-grained Images Features Representation [J]. Computer and Modernization, 2024, 0(03): 97-104.
[4]	LI Shi-da, XIANG Jian-wen. A Weakened Joint Reinforcement Method to Improve Robustness of Image Recognition Models [J]. Computer and Modernization, 2023, 0(10): 70-76.
[5]	WU Tian, LIU Hai-hua, TONG Shun-yan. Image Classification Based on Deep Feedback CNN [J]. Computer and Modernization, 2023, 0(09): 82-86.
[6]	LI Shi-qiu. A Collaborative Representation-based Method of Discriminant Locality Preserving Projections [J]. Computer and Modernization, 2023, 0(06): 43-47.
[7]	ZHU Jian-bo, GE Ming-feng, DONG Wen-fei. Alzheimer’s Disease Image Classification Based on Improved EfficientNet [J]. Computer and Modernization, 2023, 0(06): 56-61.
[8]	ZHU Li-qing, LI Xiang, . Vehicle Detection of Remote Sensing Images Based on Improved YOLOv5 Algorithm [J]. Computer and Modernization, 2023, 0(05): 117-121.
[9]	WANG Yan, YANG Feng-wei, ZHAI Xing, WANG Li, TANG Yan, LIU Zhe, HAN Ai-qing. Computer Aided Diagnostic on Microscopic Images Based on Deep Learning [J]. Computer and Modernization, 2023, 0(03): 54-59.
[10]	SHI Zhan-kun, YANG Feng, HAN Jian-ning, GUO Xin, CAO Shang-bin. Apples Recognition in Natural Environment Based on Faster-RCNN [J]. Computer and Modernization, 2023, 0(02): 62-65.
[11]	WANG Chang-jun, PENG Cheng, LI Yong. Multi-feature Fusion Ship Target Detection Algorithm in Complex Environment [J]. Computer and Modernization, 2022, 0(11): 81-88.
[12]	YIN Chu, ZHAO Qi-lin, RUI Ting, YUAN Hui, WANG Jian. Crack Target Detection Algorithm Based on Adaptive Anchor Frame [J]. Computer and Modernization, 2022, 0(11): 95-101.
[13]	LIN Hang, GENG Duo-fei, YU Hao, HU Dan, ZHANG Ke. An Insulator Self-detonation Detection Algorithm on Transmission Line Based on Double Modules [J]. Computer and Modernization, 2022, 0(07): 15-20.
[14]	XU Ya-jun, GUO En-hao, CHEN Lin, SI Cheng-ke. A Data-driven Deep Modulation Identification Method for RF Signals [J]. Computer and Modernization, 2022, 0(06): 80-86.
[15]	LI Jian, ZHANG Ke-liang, TANG Liang, XIA Rong-jing, REN Jing-jing. Data Augmentation for Chinese Named Entity Recognition Task [J]. Computer and Modernization, 2022, 0(04): 1-6.