We propose Deep Decomposition of Circularly Symmetric Gabor Wavelet (DD-CSGW) for rotation-invariant texture image classification. Circularly Symmetric Gabor Wavelet (CSGW) is rotation-invariant tool for image analysis. However, CSGW has an obvious shortcoming: it extracts less discriminative information from image due to lack of directional selectivity. We make two contributions to improve the performance of CSGW: (1) We propose deep decomposition approach of CSGW to obtain more discriminative image information; (2) Because strong scale dependencies exist in the domain of CSGW, we use copula model to capture these scale dependencies. For classification, the energies of DD-CSGW and the parameters of copula model based on DD-CSGW are used as the features of texture, and SVM is utilized as the classifier. Experiments show that DD-CSGW obviously improves the performance of CSGW, and it is effective compared with the state-of-the-art rotation-invariant methods.