Abstract | ||
---|---|---|
It is challenging to detect weak hidden information in a JPEG compressed image. In this paper, we propose a 32-layer convolutional neural networks (CNNs) with feature reuse by concatenating all features from previous layers. The proposed method can improve the flow of gradient and information, and the shared features and bottleneck layers in the proposed CNN model further reduce the number of parameters dramatically. The experimental results shown that the proposed method significantly reduce the detection error rate compared with the existing JPEG steganalysis methods, e.g. state-of-the-art XuNet method and the conventional SCA-GFR method. Compared with XuNet method and conventional method SCA-GFR in detecting J-UNIWARD at 0.1 bpnzAC (bit per non-zero AC DCT coefficient), the proposed method can reduce detection error rate by 4.33% and 6.55% respectively. |
Year | DOI | Venue |
---|---|---|
2018 | 10.23919/APSIPA.2018.8659589 | 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) |
Keywords | Field | DocType |
Transform coding,Convolution,Discrete cosine transforms,Training,Gabor filters,Distortion,Computer architecture | Bottleneck,Pattern recognition,Convolution,Convolutional neural network,Computer science,Word error rate,Transform coding,JPEG,Artificial intelligence,Deep learning,Steganalysis | Conference |
ISSN | ISBN | Citations |
2309-9402 | 978-9-8814-7685-2 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jianhua Yang | 1 | 52 | 7.10 |
Xiangui Kang | 2 | 424 | 37.76 |
Edward K. Wong | 3 | 268 | 24.19 |
Yun Q. Shi | 4 | 2918 | 199.53 |