Abstract: To provide larger capacity of the hidden secret data and to maintain a better visual quality of stego-image，a novel steganographic method based on SOM and wavelet contrast is presented.First，an image is divided into blocks，and every block is decomposed into one-level wavelet to obtain the wavelet contrast.Then，classify blocks by SOM.Finally，embed secret information with steganography based on modulus.From the experimental results，compared with WCL，the proposed method hides much more information and maintains a better visual quality of stego-image.

Key words: steganographic method, Self-Organizing Maps（SOM）, wavelet

摘要： 为了提供较大的秘密信息嵌入量和保持较好的载密图像质量，提出了一种基于自组织特征映射神经网络和小波对比度的图像密写。该方法先将载体图像分成固定大小的小块，对每一小块进行小波一级分解后计算小波对比度。然后，利用自组织特征映射神经网络将小块分为三类。最后，采用模算子技术嵌入秘密信息。实验结果表明，与WCL算法相比，该算法有更大的嵌入量并保持了良好的载密图像质量。

关键词: 密写, 自组织映射图, 小波