In this paper, we propose a novel rotation invariant texture classification technique by using ridgelet packets. Ridgelet packets provide many orthonormal bases that can effectively capture directional features present in textures. The Fourier transform is good at eliminating the texture orientation differences. By combining these two tools, a very efficient rotation invariant texture classification technique is created. Experimental results show that the proposed method achieves very high classification rates and it outperforms two state-of-the-art methods for rotation invariant texture classification under both noise-free and noisy environments.