Modified rate-distortion function with optimal classification for wavelet coding

We present a wavelet transform based coding approach by employing a modified rate-distortion function and hybrid optimum classification. In the proposed approach, each upper band subimage from wavelet decomposition is optimally classified to achieve the minimum quantization error, according to an efficient prediction model and a modified rate-distortion function. The performance of the asymptotic rate-distortion function is essential to classified VQ and bit allocation. In order to utilize an analytic form of R-D function for the bit assignment at low bit rates and keep the optimum classification achievable, a modified R-D function is proposed to approximate the real VQ behavior. The modified R-D function performs well at the bit rate of interest and reduces the computation load significantly at the bit allocation stage. A performance comparison is made with other wavelet coding schemes. It is shown that our approach is competitive with the best wavelet coding approaches proposed in the literature.