基于卷积神经网络的轻量高效图像隐写  

Lightweight and Efficient Image Steganography Based on Convolutional Neural Network

作　　者：段新涛[1,2] 白鹿伟 徐凯欧 张萌 保梦茹 武银行 秦川 DUAN Xintao;BAI Luwei;XU Kaiou;ZHANG Meng;BAO Mengru;WU Yinhang;QIN Chuan(College of Computer and Information Engineering,Henan Normal University,Xinxiang 453007,Henan,China;Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province,Xinxiang 453007,Henan,China;School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]河南师范大学计算机与信息工程学院,河南新乡453007 [2]教育人工智能与个性化学习河南省重点实验室,河南新乡453007 [3]上海理工大学光电与计算机工程学院,上海200093

出　　处：《应用科学学报》2025年第1期80-93,共14页Journal of Applied Sciences

基　　金：河南省高等学校重点科研项目(No.23A520006);河南省科技攻关计划项目(No.222102210199)资助。

摘　　要：基于深度学习的图像隐写方法,因存在模型参数量和计算量大等问题,而面临高参数和计算负载的挑战,为此提出了一种轻量高效的图像隐写方法。首先在编码器和解码器中引入Ghost模块,降低了编码器和解码器的参数量和计算量。其次提出了一个多尺度特征融合模块,用以捕捉多维数据中的复杂关系。最后提出了一个新颖的混合损失函数,可在保持模型不变的情况下提升图像隐写质量。实验结果表明,所提方法在256×256像素的图像上峰值信噪比达到47.59 dB。与目前最优的图像隐写方法相比,所提方法的隐写质量提升1.7 dB,参数量减少77%,计算量减少91%,在隐写质量上有较优的表现,同时模型的参数量和计算量大大降低,实现了模型的轻量高效化。Deep learning-based image steganography often faces challenges due to the large number of model parameters and high computational demands.In response,a lightweight and efficient image steganography method is proposed.Firstly Ghost module is introduced into the encoder and decoder,which reduces the number of parameters and computational complexity.Furthermore,a multi-scale feature fusion module is designed to capture complex relationships within multidimensional data.In addition,a novel hybrid loss function is proposed,which can improve image steganography quality without modifying the model.Experimental results show that the proposed method achieves a peak signal-to-noise ratio(PSNR)of 47.59 dB on a 256×256 pixel image.Compared with the current best image steganography method,the steganography quality is improved by 1.7 dB,the number of parameters is reduced by 77%,and number of computations by 91%.These results confirm that the proposed method effectively enhances steganography quality with reduced number of parameters and computational complexity of the model,achieving a lightweight and efficient model.

关 键 词：图像隐写 深度学习 多尺度特征融合 混合损失函数 

分 类 号：TN911.73[电子电信—通信与信息系统]