The extraction of texture features from compressed images can be cumbersome using traditional decompress-process methods. This paper proposes a method for calculating wavelet energy texture features directly from a wavelet compressed symbol stream. The proposed method requires little decompression (only arithmetic decoding is necessary) and results in a technique that is efficient and requires less memory than traditional approaches. The developed algorithm has been implemented at various compression ratios and in each case, the classification results are nearly identical to those obtained with the traditional method.