A novel selective image authentication system based on the robust digital watermarking is proposed. The discrete shearlet transform is performed in order to extract the feature vector from the image. The cone-adapted version of the transform is used to calculate the shearlet coefficients more precisely and to avoid the biased treatment. The proposed approach allows to use conventional cryptographic digital signature for the image feature vector verification and makes the authentication scheme more secure. In order to embed watermark (WM) into the image the areas HL3 and LH3 of the Haar wavelet transform coefficients are used. Experimental results show that the proposed selective image authentication system is effective in terms of tolerance to JPEG compression, malicious image tampering detection and visual image quality just after embedding.