The Design of Image Compression with BP Neural Network Based on the Dynamic Adjusting Hidden Layer Nodes

Jing Li; Xin Hui Wu; Chang Hai Qin; Jing Zhao

doi:10.4028/www.scientific.net/AMR.433-440.3797

Paper Titles

A Measurement-Based Robust Adaptive Kalman Filtering Algorithm
p.3773

Motion Path Editing Based on Constraint Detection
p.3780

Identification of Lightning Disturbance in UHVDC Transmission Lines Using Correlation Degree Based on Short Time Window Data
p.3787

Monitoring System of Weighing Fruit Grader Based on Labwindows/CVI
p.3792

The Design of Image Compression with BP Neural Network Based on the Dynamic Adjusting Hidden Layer Nodes
p.3797

Multi-Layers Agorithm of Grid Resource Discovery
p.3802

Study on Assessment Model of Lightning Proof Abilities of HV Transmission Line Based on ArcGIS
p.3808

Study of Strong Moire-Fringe Density and Direction in Noisy Phase Maps
p.3815

The Voltage Output Characteristics of New 24-Pulse Rectification System under Unbalanced Source Voltage
p.3820

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 433-440The Design of Image Compression with BP Neural...

The Design of Image Compression with BP Neural Network Based on the Dynamic Adjusting Hidden Layer Nodes

Abstract:

Aiming at the image compression algorithms with the used BP neural network ,they have inherent defects of poor universality and long training time, a model of the dynamic adjusting hidden layer nodes of BP neural network is designed. According to the training image, using the correlation coefficient and dispersion degree of the same hidden layer’s nodes, we cut and delete some no nodes, this algorithm not only can improve learning speed effectively but also has certain generalization ability, and can complete the task of no- training images compression through experiments.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 433-440)

Pages:

3797-3801

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.433-440.3797

Citation:

Cite this paper

Online since:

January 2012

Authors:

Jing Li, Xin Hui Wu, Chang Hai Qin, Jing Zhao

Keywords:

BP Neural Network (BPNN), Dynamic Adjusting, Hidden Layer Nodes, Image Compression

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] WANG Shu-yu, SHI Ning, LI Zi-Jie Image Compression Algorithm Based on PSO-BP Neural Networks, Computer Knowledge and Technology, 23 , 2007 PP1409-1411.

Google Scholar

[2] Li Xingmei Chen Lian Yan Guoping Application of artificial neural network in building degraded model of compressed image , Electronic Measurement Technology , 3, 2008 PP14-15.

Google Scholar

[3] Wang Wei, The Applications of Neural Networks to Image Coding, ACTA ELECTRONICA SINICA , 7, (1995).

Google Scholar

[4] W. Schifmann, MJoost, and R. Werner. Optimization of the backpropagation　algorithm for　training　multilayer　perceptrons. Technical　report, U niversity.

Google Scholar

[5] T . Tollenaere. Supersab: Fast adaptive back propagation with good scalingproperties. NeuralNetwork, 3(5), (1990).

Google Scholar