This paper evaluates feature extraction techniques in aspect of watermark synchronization. Most watermarking algorithms suffer from geometric distortion attacks that desynchronize the location of the inserted watermark. The process of synchronizing the location for watermark insertion and detection is crucial to design robust watermarking. One solution for watermark synchronization is to use features. This paper reviews feature extraction techniques in feature-based watermarking: the Harris corner detector and the Mexican Hat wavelet scale interaction method. We evaluate the scale-invariant keypoint extractor in comparison with others. After feature extraction, the set of triangles is generated by Delaunay tessellation. These triangles are the location for watermarking. Redetection ratio of triangles is measured against geometric distortion attacks and signal processing attacks. Experimental results show that the scale–invariant keypoint extractor is appropriate for robust watermarking.