Secure Images for Copyright by Watermarking in Transform sphere using bidirectional Neural Network

Person beings knowledge a non preventable circumstances of distribution and redistribution their pictures, documents, videos etc on the internet about every week. Intruders are frequently the ones who do not desire to work hard and they maintain on somebody’s original work. watermarking is the process of embedding data called a watermark into a multimedia object such that watermark can be detected or extracted later to make an declaration about the object. Watermarking is adding“ownership” information in multimedia inside to show the dependability. There are generally two most popular ways of embedding the watermark in the digital content i.e. spatial sphere and transform sphere. In spatial sphere, Least-Significant Bit (LSB), SSM Modulation-Based Technique has been developed. For DCT sphere, block based approach and for wavelet sphere, multi-level wavelet transformation technique and CDMA based approaches has been developed. Presented techniques based on spatial and occurrence domain suffer from the problems of low Peak Signal to Noise Ratio (PSNR) of watermark and image quality poverty in unreliable quantity. This paper offers a technique based on Back propagation Neural Network to instruct a given cover image to construct a preferred watermark image.