Results 211 to 220 of about 20,295 (253)

Pulse-Coupled Neural Networks for Contour and Motion Matchings

IEEE Transactions on Neural Networks, 2004
Two neural networks based on temporal coding are proposed in this paper to perform contour and motion matchings. Both of the proposed networks are three-dimensional (3-D) pulse-coupled neural networks (PCNNs). They are composed of simplified Eckhorn neurons and mimic the structure of the primary visual cortex.
Bo Yu 0016, Liming Zhang 0001
openaire   +2 more sources

Segmentation of medical imagery with pulse-coupled neural networks

IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), 2003
This paper discusses some of the advantages and disadvantages of pulse-coupled neural networks (PCNNs) for performing image segmentation in the realm of medical diagnostics. PCNNs were tested with magnetic resonance imagery (MRI) of the brain and abdominal region and nuclear scintigraphic ventilation/perfusion imagery of the lungs (V/Q scans).
Paul E. Keller, A. David McKinnon
openaire   +1 more source

Stereo vision using pulse-coupled neural network

Proceedings of the 41st SICE Annual Conference. SICE 2002., 2003
In this paper; a neural network model based on bioptical visual cortex; which is called pulse-coupled neural network (PCNN), is investigated. We especially focus on the segmentation ability of the PCNN. A PCNN model with signal generator is proposed to improve the segmentation ability.
Ogawa, Yuuki, Ishimura, Kosei, Wada, Mitsuo   +2 more
openaire   +1 more source

Speaker Recognition Using Pulse Coupled Neural Networks

2007 International Joint Conference on Neural Networks, 2007
Pulse coupled neural network (PCNN) is a paradigm that has not yet been explored enough in speaker recognition. This paper presents the results of experiments conducted to develop a new recognition architecture that applies PCNN to text independent speaker recognition.
Antonio Pedro Timoszczuk, Euvaldo F. Cabral Jr.   +1 more
openaire   +1 more source

Image thinning using pulse coupled neural network

Pattern Recognition Letters, 2004
PCNN-pulse coupled neural network, based on the phenomena of synchronous pulse bursts in the animal visual cortex, is different from traditional artificial neural networks. This paper first introduces a new approach for binary image thinning by using the pulse parallel transmission characteristic of PCNN. The thinning result obtains when pulses emitted
Xiaodong Gu 0001, Daoheng Yu, Liming Zhang 0001   +2 more
openaire   +1 more source

PCNNP: a pulse-coupled neural network processor

Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290), 2003
Pulse-coupled neural networks, PCNN, have arisen as an alternative for image preprocessing. However, the PCNN model is a member of the artificial neural networks model and hence it inherits the problem of parameter specification. This paper presents a PCNN model that was generated by analysis of other PCNN models and describes what we call a PCNN ...
null Chacon MMI, S.A. Zimmerman, A.D. Sanchez   +2 more
openaire   +1 more source

Pulse coupled neural networks for image processing

Proceedings IEEE Southeastcon '95. Visualize the Future, 2002
Studies of cat's and monkey's visual cortex has led to the development of pulse coupled neurons which are significantly different from the conventional artificial neurons. Pulse coupled neural networks (PCNN) are modeled to capture the essence of recent understanding of image interpretation process in biological neural systems.
H.S. Ranganath, G. Kuntimad, J.L. Johnson   +2 more
openaire   +1 more source

Reentrant pulse coupled neural networks (PCNNs)

Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94), 2002
The PCNN developed by Johnson (1993) are syntactic pattern transformers. Hence their outputs are quite similar over a wide variety of "distortions". We show that we can convert a PCNN into an attractor system which, away from boundaries, produces point attractor icons which are ideal inputs to statistical pattern processors. >
F. Allen, H.J. Caulfield
openaire   +1 more source

Pulse Coupled Neural Network Based Image Fusion

2005
For the pulse-coupled neural network (PCNN) has an inherent ability to segment images, we present a multisensor image fusion scheme based on PCNN in this paper. The algorithm adopts salience and visibility as two extracted features for each segmented region to determine the fusion weight.
Min Li, Wei Cai, Zheng Tan
openaire   +1 more source

Learning algorithm for pulse coupled neural network

Proceedings of Thirtieth Southeastern Symposium on System Theory, 2002
Living neurons act as leaky integrators in that they store on their surface signals applied to them in previous fractions of a second. For large pyramidal neurons in the cortex the time constant of the cell membrane may be higher than had previously been thought and the temporal properties of the neurons need to be reassessed in this light. In any case,
P. Calvin, G. Yuen, M. Boddruzzaman, M. Malkani   +3 more
openaire   +1 more source