Journal of Jilin University(Engineering and Technology Edition) ›› 2021, Vol. 51 ›› Issue (5): 1838-1844.doi: 10.13229/j.cnki.jdxbgxb20210400

Previous Articles    

Image manipulation localization algorithm based on channel attention convolutional neural networks

Hui ZHONG1(),Heng KANG2,Ying-da LYU3,Zhen-jian LI1,Hong LI1,Ruo-chuan OUYANG1   

  1. 1.Management Center of Big Data and Network，Jilin University，Changchun 130012，China
    2.ZICT Technology Co. ，Ltd. ，Shenzhen 518000，China
    3.Center for Computer Fundamental Education，Jilin University，Changchun 130012，China
  • Received:2021-05-06 Online:2021-09-01 Published:2021-09-16
  • Contact: Ying-da LYU E-mail:zhongh@jlu.edu.cn

RICH HTML

 26   

PDF (PC)

271

Abstract:

To prevent manipulation of image content （such as splicing）， this paper proposes an image manipulation localization algorithm based on Channel Attention Convolutional Neural Network， and it is called CA-Net. Although the powerful feature learning and mapping capabilities of CNNs can sequentially acquire rich spatial features， this paper proposes to use parallel dilated convolutional layers with different sampling steps to extract multi-scale features. At the same time， in order to make better use of the characteristic channel information， we additionally introduce a channel attention module in the decoding network. This experiment uses Synthesized image dataset for training， and fine-tunes and tests NC2016 and CASIA on the two image libraries. Experimental results show that the proposed parallel dilated convolutional layer and channel attention module can significantly improve the results. Compared with some of the state-of-the-art algorithms， CA-Net performs best on the two standard image datasets.

Key words: channel attention, convolutional neural networks, image manipulation localization, feature extraction

CLC Number: 

  • TP391

Fig.1

Architecture of our CA-Net"

Fig.2

Structure of channel attention module with residual connection"

Table 1

Number of training and test images in image datasets"

SynthesizedNC2016CASIA
训练集65 0004045123 （CASIA v2.0）
测试集-160921 （CASIA v1.0）

Table 2

Results of choices of dilated convolutional layer"

孔洞卷积层准确率/%

采样步长｛1，3，5，7｝

采样步长｛2，4，6，8｝

常规卷积层

94.32
93.22
92.13

Table 3

Results of CA-Net with or without channel attention module"

通道注意力模块准确率/%
CA_090.15
CA_192.76
CA_293.17
CA_3（本文算法）94.32

Table 4

Pixel level F1 comparison on two datasets"

算法F1
NC2016CASIA v1.0
Error Level Analysis0.2360.214
Noise Inconsistencies0.2850.263
CFA0.1740.207
LSTM-EnDec-0.391
RGB-N0.7220.408
CA_3（本文算法）0.7950.425

Table 5

Pixel level AUC comparison on two datasets"

算法AUC/%
NC2016CASIA v1.0
Error Level Analysis42.961.3
Noise Inconsistencies48.761.2
CFA50.152.2
J-Conv-LSTM-Conv76.4-
LSTM-EnDec79.376.2
ManTra-Net79.581.7
CA_3（本文算法）83.181.9

Fig.3

Qualitative visualization for image manipulation detection on NC2016 and CASIA v1.0 datasets"

1 赵宏伟, 刘晓涵, 张媛, 等. 基于关键点注意力和通道注意力的服装分类算法[J]. 吉林大学学报: 工学版, 2020, 50(5): 1765-1770.
Zhao Hong-wei, Liu Xiao-han, Zhang Yuan, et al. Clothing classification algorithm based on landmark attention and channel attention[J]. Journal of Jilin University(Engineering and Technology Edition), 2020,50(5): 1765-1770.
2 Zhuang P, Li H, Tan S, et al. Image tampering localization using a dense fully convolutional network[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 2986-2999.
3 Ng T T, Chang S F, Sun Q. Blind detection of photomontage using higher order statistics[C]∥International Symposium on Circuits and Systems, Canada, 2004: 8189867.
4 Verdoliva L. Media forensics and deepfakes: an overview[J]. IEEE Journal of Selected Topics in Signal Processing, 2020, 14(5): 910-932.
5 Gaborini L, Bestagini P, Milani S, et al. Multi-clue image tampering localization[C]∥IEEE International Workshop on Information Forensics and Security, Atlanta, 2014: 125-130.
6 Ferrara P, Bianchi T, Rosa A D, et al. Image forgery localization via fine-grained analysis of CFA artifacts[J]. IEEE Transactions on Information Forensics and Security, 2012, 7(5): 1566-1577.
7 Amerini I, Uricchio T, Ballan L, et al. Localization of JPEG double compression through multi-domain convolutional neural networks[C]∥IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, 2017: 1865-1871.
8 Salloum R, Ren Y, Kuo C-C J. Image splicing localization using a multi-task fully convolutional network[J]. Journal of Visual Communication Image Representation, 2018, 51: 201-209.
9 Bappy J H, Simons C, Nataraj L, et al. Hybrid LSTM and Encoder-Decoder architecture for detection of image forgeries[J]. IEEE Transactions on Image Processing, 2019, 28(7): 3286-3300.
10 陈绵书, 于录录, 苏越, 等. 基于卷积神经网络的多标签图像分类[J]. 吉林大学学报: 工学版, 2020, 50(3): 1077-1084.
Chen Mian-shu, Yu Lu-lu, Su Yue, et al. Multi-label images classification based on convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(3): 1077-1084.
11 Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module[C]∥Proceedings of Europeon Conference on Computer Vision, Cham, Springer: 2018: 3-19.
12 Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[C]∥International Conference on Medical Image Computing and Computer-Assisted Intervention, Cham, Springer: 2015: 234-241.
13 Wu Y, Abd-Almageed W, Natarajan P. Deep matching and validation network: an end-to-end solution to constrained image splicing localization and detection[C]∥Proceedings of the 25th ACM International Conference on Multimedia, CA, 2017: 1480-1502.
14 Chen L, Papandreou G, Kokkinos I, et al. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs[J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2017, 40(4): 834-848.
15 Badrinarayanan V, Kendall A, Cipolla R. Segnet: a deep convolutional encoder-decoder architecture for scene segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
16 Kingma D P, Ba J. Adam: a method for stochastic optimization[C]∥3rd International Conference for Learning Representations, San Diego, 2015: arXiv:.
17 Guan H, Kozak M, Robertson E, et al. MFC datasets: large-scale benchmark datasets for media forensic challenge evaluation[C]∥IEEE Winter Applications of Computer Vision Workshops, Waikoloa, 2019: 63-72.
18 Dong J, Wang W, Tan T. Casia image tampering detection evaluation database[C]∥IEEE China Summit and International Conference on Signal and Information Processing, Beijing, 2013: 422-426.
19 Chen L, Papandreou G, Kokkinos I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
20 Luo W, Huang J, Qiu G. JPEG error analysis and its applications to digital image forensics[J]. IEEE Transactions on Information Forensics & Security, 2010, 5(3): 480-491.
21 Mahdian B, Saic S. Using noise inconsistencies for blind image forensics[J]. Image and Vision Computing, 2009, 27(10): 1497-1503.
22 Zhou P, Han X, Morariu V, et al. Learning rich features for image manipulation detection[C]∥Proceedings of IEEE Conference Computer Vision and Pattern Recognition, Salt Lake City, 2018: 1053-1061.
23 Bappy M, Roy-Chowdhury A K, Bunk J, et al. Exploiting spatial structure for localizing manipulated image regions[C]∥IEEE International Conference on Computer Vision, Venice, 2017: 17467965.
24 Wu Y, Abdalmageed W, Natarajan P. Mantra-Net: manipulation tracing network for detection and localization of image forgeries with anomalous features[C]∥Proceedings of IEEE Conference Computer Vision and Pattern Recognition, Long Beach, 2019: 9543-9552.
[1] Hou⁃jie LI,Fa⁃sheng WANG,Jian⁃jun HE,Yu ZHOU,Wei LI,Yu⁃xuan DOU. Pseudo sample regularization Faster R⁃CNN for traffic sign detection [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1251-1260.
[2] Xiao-long ZHU,Zhong XIE. Automatic construction of knowledge graph based on massive text data [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1358-1363.
[3] Tao XU,Ke MA,Cai-hua LIU. Multi object pedestrian tracking based on deep learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(1): 27-38.
[4] Yi-bin LI,Jia-min GUO,Qin ZHANG. Methods and technologies of human gait recognition [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(1): 1-18.
[5] GENG Qing-tian, YU Fan-hua, WANG Yu-ting, GAO Qi-kun. New algorithm for vehicle type detection based on feature fusion [J]. 吉林大学学报(工学版), 2018, 48(3): 929-935.
[6] DONG Qiang, LIU Jing-hong, ZHOU Qian-fei. Improved SURF algorithm used in image mosaic [J]. 吉林大学学报(工学版), 2017, 47(5): 1644-1652.
[7] YIN Ming, ZHAN Yin-wei, PEI Hai-long. Co-sparse analysis operator learning for image fusion [J]. 吉林大学学报(工学版), 2016, 46(6): 2052-2058.
[8] XIAO Zhong-jie. Recognition of digital image based on wavelet space feature spectrum entropy [J]. 吉林大学学报(工学版), 2015, 45(6): 1994-1998.
[9] LIU Hong,SUN Shuang-zi,WANG Qing-yuan,LI Yan-zhong. PSO based feature extraction method for analog circuit fault information [J]. 吉林大学学报(工学版), 2015, 45(2): 675-680.
[10] PAN Hai-yang, LIU Shun-an, YAO Yong-ming. Depth information-basd autonomous aerial refueling [J]. 吉林大学学报(工学版), 2014, 44(6): 1750-1756.
[11] GU Bo-yu,SUN Jun-xi,LI Hong-zuo,LIU Hong-xi,LIU Guang-wen. Face recognition based on eigen weighted modular two-directional two-dimensional PCA [J]. 吉林大学学报(工学版), 2014, 44(3): 828-833.
[12] WANG Zhuo-zheng, JIA Ke-bin. Application of matrix completion and principal component analysis to corrupted image registration [J]. 吉林大学学报(工学版), 2013, 43(增刊1): 78-83.
[13] SHI Dong-cheng, ZHENG Chao. Eye states detection algorithm based on phase information [J]. 吉林大学学报(工学版), 2013, 43(增刊1): 265-269.
[14] ZHAO Hong-wei, CHEN Xiao, LONG Man-li, PEI Shi-hui. Image edge detection based on Riesz transformation [J]. 吉林大学学报(工学版), 2013, 43(增刊1): 133-137.
[15] ZHANG Xu, GUO Bao-long, MENG Fan-jie, SUN Wei. Image retrieval based on IPDSH and region division [J]. 吉林大学学报(工学版), 2013, 43(05): 1408-1414.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd