A genetic algorithm based robust blind digital watermarking scheme is presented. Starting from a binary image (the original watermark), a genetic algorithm is performed searching for a permutation of this image which is as uncorrelated as possible to the original watermark. The output of the GA is used as our final watermark, so that both security and robustness in the watermarking process is improved. Now, the original cover image is partitioned into non-overlapped square blocks (depending on the size of the watermark image). Then a (possibly extended) Hadamard transform is applied to these blocks, so that one bit information from the watermark image is embedded in each block by modifying the relationship of two coefficients in the transformed matrices. The watermarked image is finally obtained by simply performing the inverse (extended) Hadamard transform on the modified matrices. The experimental results show that our scheme keeps invisibility, security and robustness more likely than other proposals in the literature, thanks to the GA pretreatment.