论文信息 - Feature generation improving by optimized PCNN

Feature generation improving by optimized PCNN

The paper analyses disadvantages of standard feature generation and their standardization for image recognition by pulse coupled neural network (PCNN). The aim of research was to propose a new form of feature value calculation that improves significantly the quality of generated features. It is part of algorithm for feature generation by optimized PCNN.

I. Mokris | R. Forgac

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

[2] I. Mokris,et al. Parameter influence of pulse coupled neural network for image recognition , 2001 .

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

[4] John L. Johnson,et al. Stabilized input with a feedback pulse‐coupled neural network , 1996 .

[5] Jason M. Kinser,et al. Pulse image processing using centripetal autowaves , 2000, SPIE Defense + Commercial Sensing.

[6] J. L. Johnson. Pulse-coupled neural nets: translation, rotation, scale, distortion, and intensity signal invariance for images. , 1994, Applied optics.

[7] Jason M. Kinser,et al. Simplified pulse-coupled neural network , 1996, Defense + Commercial Sensing.

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

[9] Jason M. Kinser,et al. Implementation of pulse-coupled neural networks in a CNAPS environment , 1999, IEEE Trans. Neural Networks.

[10] Thomas Lindblad,et al. Parameter adaptation in a simplified pulse-coupled neural network , 1999, Other Conferences.