Results 141 to 150 of about 740 (176)
Some of the next articles are maybe not open access.
Face Recognition Algorithm Based on Weighted Intensity PCNN
2020 Eighth International Conference on Advanced Cloud and Big Data (CBD), 2020Face recognition is an important identification technology in daily life and one of the research hotspots in the field of computer vision and intelligent image processing. However, many algorithms based on Pulse Coupled Neural Network (PCNN) do not adequately describe features, same parameters are used to process the entire face image, ignoring the ...
Hongxia Deng +5 more
openaire +1 more source
Dense Stereo Matching Based on PCNN
2009 First International Conference on Information Science and Engineering, 2009A key problem in stereo matching lies in selecting an appropriate window size. This paper presents a new method based on using small window for first-step matching and Pulse Coupled Neural Network for perfecting disparity maps. Our algorithm not only reflects the predominance that small window achieves sharper counter, but also gains accurate depth of ...
Xiao Shu, Chenhui Yang, Hui Liu
openaire +1 more source
A New Method of Parameters Determined in PCNN
Applied Mechanics and Materials, 2014The aim of this paper is to research the image recognition system and its applications, which is based on combining the traditional BP neural networks and the third-generation pulse coupled neural network (PCNN).The process is by extracting the image's time and entropy sequences, then through the fast Fourier transform, and finally as inputs of the ...
Shui Ming He, Dian Hong Wang
openaire +1 more source
Multispectral and Panchromatic Images Fusion by Adaptive PCNN
2010As for low resolution of remote sensing images, a novel image fusion algorithm by adaptive PCNN was proposed. The multi-spectral image is firstly converted from RGB to lαβ color space. Then, the input images are adaptively decomposed by simplifying traditional PCNN model and defining image definition as the coupled joint coefficient.
Yong Li, Ke Wang, Da-ke Chen
openaire +1 more source
Gaussian noise filter based on PCNN
International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003, 2003The pulse coupled neural network (PCNN) has gained wide research as a new artificial neural network. It was derived directly from the study of the small mammal's visual cortex. PCNN is a model with multiple parameters, and finding the proper values of these parameters is an onerous task.
null Ma Yi-de +2 more
openaire +1 more source
Palm print image processing with PCNN
SPIE Proceedings, 2010Pulse coupled neural networks (PCNN) is based on Eckhorn's model of cat visual cortex, and imitate mammals visual processing, and palm print has been found as a personal biological feature for a long history. This inspired us with the combination of them: a novel method for palm print processing is proposed, which includes pre-processing and feature
Jun Yang, Xianhong Zhao
openaire +1 more source
PCNN-DDF Filter for Color Image
2012This chapter presents a new filtering approach capable of detecting and removing impulsive noise in multi-channel images. The filter detects noise pixels in the image by utilizing pulse-coupled neural networks specific feature that the fire of one neuron can capture firing of its adjacent neurons due to their spatial proximity and intensity similarity.
Beiji Zou, Haoyu Zhou, Hao Chen, Cao Shi
openaire +1 more source
Recognition method for apple fruit based on SUSAN and PCNN
Multimedia Tools and Applications, 2017This study proposes a recognition method for apple fruit based on SUSAN (Smallest univalues segment assimilating nucleus) and PCNN (Pulse coupled neural network) to accurately identify and locate fruit targets. First, homomorphic filtering is used to conduct image enhancement by considering the influence of different lighting conditions on the ...
Liming Xu, Jidong Lv
openaire +1 more source
A new method of parameters determined in image recognition by PCNN
2011 2nd International Conference on Control, Instrumentation and Automation (ICCIA), 2011The aim of this paper is to research the image recognition system and its applications, which is based on combining the traditional BP neural networks and the third-generation pulse coupled neural network (PCNN).The process is by extracting the image's time and entropy sequences, then through the fast Fourier transform, and finally as inputs of the ...
Shuiming He, Dianhong Wang
openaire +1 more source
Frequency-domain characteristic analysis of PCNN
The Journal of Supercomputing, 2023Xiangyu Deng +2 more
openaire +1 more source