Texture-image classification with rotation-invariance in compressed-domain

A novel method of texture-image classification with rotation-invariauce in DCT compressed-domain is proposed. By reordered the DCT coefficients for multi-resolution, the textnral features are extracted in DCT transformed-domain and these textural features can be used to classify texture-images in RLE bit-stream directly with rotation-invariancc. The experimental results demonstrate that texture-images can be classified at higher correct classification rate.