Convolutional neural network-based image watermarking using discrete wavelet transform

With the growing popularity of Internet, digital images are used and transferred more frequently. Although this phenomenon facilitates easy access to information, it also creates security concerns violates intellectual property rights by allowing illegal use, copying, content theft. Using watermarks in is one most common ways maintain security. Watermarking proving declaring ownership an image adding a watermark original image. Watermarks can be either text or placed overtly covertly expected challenging remove. This paper proposes combination convolutional neural networks (CNNs) wavelet transforms obtain watermarking network for embedding extracting watermarks. The independent host resolution, accept all kinds watermarks, has only 11 layers while keeping performance. Performance measured two terms; similarity between extracted watermarked one.