Results 131 to 140 of about 740 (176)

Synchronized oscillation and dynamical clustering in chaotic PCNN

Proceedings of the 41st SICE Annual Conference. SICE 2002., 2003
Chaotic synchronization of pulse-coupled neural network (PCNN) is studied from the viewpoint of flexible information coding. Using extended Eckhorn's PCNN model, we numerically analyze a generation of chaotic synchronized clusters in a network with locally-excitatory-globally-inhibitory connection.
Yamaguchi, Yutaka, Ishimura, Kosei, Wada, Mitsuo   +2 more
openaire   +1 more source

Simplified PCNN and Its Periodic Solutions

2004
PCNN-Pulse Coupled Neural Network, a new artificial neural network based on biological experimental results, can be widely used for image processing. The complexities of the PCNN’s structure and its dynamical behaviors limit its application so simplification of PCNN is necessary. We have used simplified PCNNs to efficiently process image. In this paper
Xiaodong Gu 0001, Liming Zhang 0001, Daoheng Yu   +2 more
openaire   +1 more source

Color image enhancement based on HVS and PCNN

Science China Information Sciences, 2010
To enhance color images more effectively, a novel strategy is presented in this paper. We firstly translate the image to be enhanced from RGB space into HIS space, secondly keep its H component unchanged, and thirdly stretch its S component exponentially, and at last process its I component in the following manner: couple both the gray value and the ...
Yudong Zhang 0001, Lenan Wu, Shuihua Wang, Geng Wei   +3 more
openaire   +1 more source

Face Recognition Scheme based on HSI-PCNN

Journal of Multimedia, 2013
By converting color face image into HSI color space from RGB color space, getting face image templates of H, S, I three channels, using HSI-PCNN algorithm extracts facial feature sequence of three channels, the feature sequence can be used for face recognition.
Xi Li, Hong Zheng, Cao Liu
openaire   +1 more source

FPGA Implementation of PCNN Algorithm

2010
The PCNN image processing algorithms are generally programmed on PC platform [1], [2]. These algorithms have fully demonstrated their outstanding performance. With the development of large-scale integrated circuit technology, the hardware implementation of neural network becomes more and more imperative.
Yide Ma, Kun Zhan, Zhaobin Wang
openaire   +1 more source

Fingerprint segmentation based on PCNN and morphology

2009 International Conference on Communications, Circuits and Systems, 2009
As an important step in an automatic fingerprint recognition system, fingerprint segmentation aims to extract the foreground of a fingerprint image in an efficient way. In this paper, an initiative algorithm for fingerprint segmentation is presented. First, the model of Pulse Coupled Neural Networks (PCNN) is utilized to binarize the fingerprint image.
null Zheng Ma, null Mei Xie, null Chengpu Yu   +2 more
openaire   +1 more source

Multiscale fusion and aggregation PCNN for 3D shape recovery

Information Sciences, 2020
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Tao Yan, Peng Wu, Yuhua Qian, Zhiguo Hu, Fengxian Liu   +4 more
openaire   +1 more source

Edge detection method based on PCNN

2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP), 2014
Pulse-Coupled Neural Network is known as third generation artificial neural network. It is created by visual cortex neurons, a synchronous pulse release phenomenon of mammals. Compare to traditional artificial neural network, PCNN has the characteristics of dynamic neural network, integrated space-time, automatic propagation and synchronous pulse ...
Xiaolong Tang, Zhongyu Tao, Panshi Tang, Jianping Li   +3 more
openaire   +1 more source

Feature generation improving by optimized PCNN

2008 6th International Symposium on Applied Machine Intelligence and Informatics, 2008
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.
R. Forgac, I. Mokris
openaire   +1 more source

Image segmentation based on PCNN model

2014 11th International Computer Conference on Wavelet Actiev Media Technology and Information Processing(ICCWAMTIP), 2014
Image segmentation is very important in image processing which can segment the images into the different parts, thus, we can focus on the parts in which we are interested. Recent years, there are many models using for the image segmentation, Pulse Coupled Neural Networks model is very popular model which is widely used among many models. Although, PCNN
Zhongyu Tao, Xiaolong Tang, Binyu Zhang, Panshi Tang, Yue Tan   +4 more
openaire   +1 more source