Results 221 to 230 of about 20,295 (253)
Some of the next articles are maybe not open access.
Pulse-coupled neural network implementation in FPGA
SPIE Proceedings, 1998Pulse Coupled Neural Networks (PCNN) are biologically inspired neural networks, mainly based on studies of the visual cortex of small mammals. The PCNN is very well suited as a pre-processor for image processing, particularly in connection with object isolation, edge detection and segmentation.
Joakim T. A. Waldemark +5 more
openaire +1 more source
VLSI architecture for analog bidirectional pulse-coupled neural networks
Proceedings of International Conference on Neural Networks (ICNN'97), 2002A compact architecture for analog CMOS VLSI implementation of voltage-mode pulse-coupled neural network (PCNN) is presented. The main feature of the proposed neuron circuit is that the structure is compact, yet exhibiting all the basic properties of natural biological neurons.
Yasuhiro Ota, Bogdan M. Wilamowski
openaire +1 more source
Image Shadow Removal Using Pulse Coupled Neural Network
IEEE Transactions on Neural Networks, 2005This paper introduces an approach for image shadow removal by using pulse coupled neural network (PCNN), based on the phenomena of synchronous pulse bursts in the animal visual cortexes. Two shadow-removing criteria are proposed. These two criteria decide how to choose the optimal parameter (the linking strength beta).
Xiaodong Gu 0001 +2 more
openaire +2 more sources
Analysis of Recurrent Networks of Pulse-Coupled Noisy Neural Oscillators
SIAM Journal on Applied Dynamical Systems, 2010Synchronization of neural oscillators has been well studied by both theorists and experimentalists. However, realistic details are often disregarded for tractability. Here, we consider a recurrent network of pulse-coupled neural oscillators since synaptic communication is often mediated by spikes.
Cheng Ly, G. Bard Ermentrout
openaire +1 more source
Digital halftoning using a modified pulse-coupled neural network
SPIE Proceedings, 2011We report the application of modified pulse-coupled neural network (PCNN) models as an image processing tool to improve the quality of digital halftoning. Four factors including weight matrice, internal activity computation, type of error diffusion and linking coefficient were researched and optimized in terms of the PSNR metric and visual inspection
Huawei Duan, Guang-xue Chen
openaire +1 more source
An adaptive method for image filtering with pulse-coupled neural networks
IEEE International Conference on Image Processing 2005, 2005Pulse coupled neural network (PCNN) has a specific feature that the fire of one neuron can capture its adjacent neuron to fire due to their spatial proximity and intensity similarity. In this paper, it is indicated that this feature itself is a very good mechanism for image filtering when the image is damaged with pet and salt type noise (PASN).
Junying Zhang, Jiyang Dong, Meihong Shi
openaire +1 more source
Review of Image Fusion Based on Pulse-Coupled Neural Network
Archives of Computational Methods in Engineering, 2015zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Wang, Zhaobin +3 more
openaire +1 more source
Hierarchical simulation of pulse-coupled neural networks
The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04., 2004Analysis of pulse-coupled neural networks (PNN) with conventional simulation tools is quite difficult due to their complexity. To use an applied simulation system it is advantageous to partition and map the different algorithms parts into segments. Segments can then be exchanged easily to analyse different realisations.
openaire +1 more source
Application of heterogeneous pulse coupled neural network in image quantization
Journal of Electronic Imaging, 2016On 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 ...
Yi Huang +3 more
openaire +1 more source
MR Image Registration Based on Pulse-Coupled Neural Networks
2007A new algorithm for magnet resonance (MR) image registration is proposed based on a modified Pulse-Coupled Neural Networks (PCNN's). The transformed image and reference image are applied as inputs to two modified networks with the same parameters respectively. Taking advantage of translation, rotation, and distortion invariant characteristics of PCNN's,
Qiu, Z. Y., Dong, J. Y., Chen, Z.
openaire +1 more source