Image compression based on growing hierarchical Self-Organizing Maps

Self-Organizing Maps (SOM) have some problems related to its fixed topology and its lack of representation of hierarchical relations among input data. Growing Hierarchical SOMs (GHSOM) solve these limitations by generating a hierarchical architecture that is automatically determined according to the input data and reflects the inherent hierarchical relations among them. These advantages can be utilized to perform a compression of an image, where the size of the codebook (leaf neurons in the hierarchy) is automatically established. Moreover, this hierarchy provides a different compression at each layer, where the deeper the layer, the lower the compression rate and the higher the quality of the compressed image. Thus, different trade-offs between compression rate and quality are given by the architecture. Also, the size of the codebooks and the depth of the hierarchy can be controlled by two parameters. In this paper, a new approach for image compression based on the GHSOM model is proposed. Experimental results confirm its good performance.