A robust and geometric invariant digital image watermarking scheme based on feature extraction and local Zernike transform is proposed in this paper. The Adaptive Harris Detector is proposed to extract feature patches for watermarking use. A local Zernike moments-based watermarking scheme is raised, where the watermarked patches can be obtained directly by inverse Zernike Transform. Each extracted circular patch is decomposed into a collection of binary patches and Zernike transform is applied to the appointed binary patches. Magnitudes of the local Zernike moments are calculated and modified to embed the watermarks. Inverse Zernike transform is applied to reconstruct the watermarked binary patch. Experimental results show that the proposed scheme is very robust against geometric distortion such as rotation, scaling, cropping, and affine transformation, and common signal processing.