Hiding Data in VQ-Compressed Images Using Pairwise Nearest Codewords Based on Minimum Spanning Tree

This paper proposes a novel codebook clustering method based on the minimum spanning tree (MST). The proposed MST-based method improves stego-image quality using the pairwise nearest clustering embedding (PNCE) method proposed by Lin and Wang. In addition, the proposed method does not take as much running time as the genetic algorithm based method proposed by Wang et al. The experimental results show that the proposed scheme is able to embed the information more effectively and efficiently.