Digital watermarking has emerged as a leading technique for copyright protection or authentication of multimedia data. It is known that there is a trade off between the imperceptibility and robustness of a digital watermarking scheme. Trying to deal with this problem, an adaptive improved singular value decomposition-based watermarking method by applying local image statistics and the genetic algorithm is presented. The local image statistics can be used not only to measure the perceptibility of watermarks once they are embedded, but also to control the perceptibility during the embedding process. Watermarking components with proper strength factors are the most critical aspect in the whole process and the genetic algorithm is employed to find the appropriate watermarking strength factors. Experimental results confirm the imperceptibility of the proposed method and its robustness against a variety of image-processing attacks.