Rate distortion optimized curve determination for curved wavelet image coding

The curved wavelet transform (CWT) was developed to enhance compactness of the wavelet transform (WT) representation. Curve determination is critical for the CWT because a well-defined curve set can increase the performance gain in terms of the rate-distortion (R-D). Conventionally, the image to be encoded is divided into blocks and the curve orientation in each block is independently determined through the minimization of its high-pass CWT energy. In this paper, we propose an R-D optimization algorithm for the curve determination, in which variable block size and the impact of neighboring blocks are taken into account. To reduce the computational cost, an alternative sampling strategy is exploited. Experiment results with natural images show that the proposed algorithm can provide better image quality, measured objectively or subjectively, compared to the conventional CWT coding algorithm. Importantly, the proposed approach overcomes the hurdles of computational cost and optimization at the global level opens the door for further performance enhancements of applications with the CWT.