Application of heterogeneous pulse coupled neural network in image quantization

Yi Huang; Yide Ma; Shouliang Li; Kun Zhan

doi:10.1117/1.JEI.25.6.061603

Translator Disclaimer

8 August 2016 Application of heterogeneous pulse coupled neural network in image quantization

Yi Huang, Yide Ma, Shouliang Li, Kun Zhan

Author Affiliations +

J. of Electronic Imaging, 25(6), 061603 (2016). https://doi.org/10.1117/1.JEI.25.6.061603

Abstract

On the basis of the different strengths of synaptic connections between actual neurons, this paper proposes a heterogeneous pulse coupled neural network (HPCNN) algorithm to perform quantization on images. HPCNNs are developed from traditional pulse coupled neural network (PCNN) models, which have different parameters corresponding to different image regions. This allows pixels of different gray levels to be classified broadly into two categories: background regional and object regional. Moreover, an HPCNN also satisfies human visual characteristics. The parameters of the HPCNN model are calculated automatically according to these categories, and quantized results will be optimal and more suitable for humans to observe. At the same time, the experimental results of natural images from the standard image library show the validity and efficiency of our proposed quantization method.

Citation Download Citation

Yi Huang, Yide Ma, Shouliang Li, and Kun Zhan "Application of heterogeneous pulse coupled neural network in image quantization," Journal of Electronic Imaging 25(6), 061603 (8 August 2016). https://doi.org/10.1117/1.JEI.25.6.061603

Published: 8 August 2016

ACCESS THE FULL ARTICLE