论文信息 - A PCNN Based Approach to Image Segmentation Using Size-Adaptive Texture Features

A PCNN Based Approach to Image Segmentation Using Size-Adaptive Texture Features

Pulse Coupled Neural Network (PCNN) and its modified forms are widely applied to image segmentation. However, most PCNN based methods are difficult in segmentation of the regions that contain rich texture information in a complex image. This paper proposes an improved approach to image segmentation based on simplified region growing PCNN with adaptive texture features input. It shows promising results to process regions with complex texture.

[1] Heggere S. Ranganath,et al. Perfect image segmentation using pulse coupled neural networks , 1999, IEEE Trans. Neural Networks.

[2] Lijuan Duan,et al. A new approach to image segmentation based on simplified region growing PCNN , 2008, Appl. Math. Comput..

[3] Manfred Opper,et al. Region growing with pulse-coupled neural networks: an alternative to seeded region growing , 2002, IEEE Trans. Neural Networks.

[4] John L. Johnson,et al. PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[5] Reinhard Eckhorn,et al. Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex , 1990, Neural Computation.

[6] Daoheng Yu,et al. A new approach for automated image segmentation based on unit-linking PCNN , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.