PCEP: Few-Shot Model-Based Source Camera Identification

被引:5
作者
Wang, Bo [1 ]
Yu, Fei [1 ]
Ma, Yanyan [1 ]
Zhao, Haining [1 ]
Hou, Jiayao [1 ]
Zheng, Weiming [1 ]
机构
[1] Dalian Univ Technol, Sch Informat & Commun Engn, Dalian 116024, Peoples R China
基金
中国国家自然科学基金;
关键词
source camera identification; few-shot; prototype construction; ensemble projection; INVARIANT TEXTURE CLASSIFICATION; VIRTUAL SAMPLE GENERATION;
D O I
10.3390/math11040803
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Source camera identification is an important branch in the field of digital forensics. Most existing works are based on the assumption that the number of training samples is sufficient. However, in practice, it is unrealistic to obtain a large amount of labeled samples. Therefore, in order to solve the problem of low accuracy for existing methods in a few-shot scenario, we propose a novel identification method called prototype construction with ensemble projection (PCEP). In this work, we extract a variety of features from few-shot datasets to obtain rich prior information. Then, we introduce semi-supervised learning to complete the construction of prototype sets. Subsequently, we use the prototype sets to retrain SVM classifiers, and take the posterior probability of each image sample belonging to each class as the final projection vector. Finally, we obtain classification results through ensemble learning voting. The PCEP method combines feature extraction, feature projection, classifier training and ensemble learning into a unified framework, which makes full use of image information of few-shot datasets. We conduct comprehensive experiments on multiple benchmark databases (i.e., Dresden, VISION and SOCRatES), and empirically show that our method achieves satisfactory performance and outperforms many recent methods in a few-shot scenario.
引用
收藏
页数:16
相关论文
共 50 条
[31]   Stroke-Based Few-Shot Chinese Character Style Transfer [J].
Liu, Guanghao ;
Zhong, Yixin ;
Chen, Yuehui ;
Cao, Yi ;
Zhao, Yaou .
ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT XI, ICIC 2024, 2024, 14872 :193-202
[32]   INTERPRETABLE CONCEPT-BASED PROTOTYPICAL NETWORKS FOR FEW-SHOT LEARNING [J].
Zarei, Mohammad Reza ;
Komeili, Majid .
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, :4078-4082
[33]   Multimodal fusion based few-shot network intrusion detection system [J].
Xu, Congyuan ;
Zhan, Yong ;
Wang, Zhiqiang ;
Yang, Jun .
SCIENTIFIC REPORTS, 2025, 15 (01)
[34]   Convolutional Siamese neural network for few-shot multi-view face identification [J].
Meddad, Majdouline ;
Moujahdi, Chouaib ;
Mikram, Mounia ;
Rziza, Mohammed .
SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (06) :3135-3144
[35]   Heterogeneous Pseudo-Supervised Learning for Few-shot Person Re-Identification [J].
Zhao, Jing ;
Lan, Long ;
Huang, Da ;
Ren, Jing ;
Yang, Wenjing .
NEURAL NETWORKS, 2022, 154 :521-537
[36]   A Novel Method for Few-Shot Specific Emitter Identification in Non-Cooperative Scenarios [J].
Xie, Cunxiang ;
Zhang, Limin ;
Zhong, Zhaogen .
IEEE ACCESS, 2023, 11 :11934-11946
[37]   Convolutional Siamese neural network for few-shot multi-view face identification [J].
Majdouline Meddad ;
Chouaib Moujahdi ;
Mounia Mikram ;
Mohammed Rziza .
Signal, Image and Video Processing, 2023, 17 :3135-3144
[38]   A Few-shot Road Extraction Method Using Customized Segment Anything Model [J].
Guo, Chen ;
Hao, Keran ;
Zuo, Chen .
2024 9TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND SIGNAL PROCESSING, ICSP, 2024, :1036-1039
[39]   A few-shot learning model for renewable energy transmission fault diagnosis in tunnels [J].
Zhang, Zhuofan ;
Cai, Dongsheng ;
Ukwuoma, Chiagoziem C. ;
Huang, Qi .
ELECTRIC POWER SYSTEMS RESEARCH, 2025, 247
[40]   Prompt-based Few-shot Learning for Table-based Fact Verification [J].
Hou, Lei ;
Liu, Yubo ;
Wu, Jie ;
Hou, Mengshu .
2022 5TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING, MLNLP 2022, 2022, :14-19