According to the image feature extraction capacity based on wavelet transformation and the nonlinear, self-adaptive and pattern recognition capacity based on artificial neural networks, the image auto-focusing method based on artificial neural networks is put forward. The wavelet components' statistics obtained by the wavelet transform are taken as the inputs of the 5 layer BP neural network model. The model identifies the image definition applying the steepest descent method of the additional momentum in a variable step to adjust the network weights. The model is first trained by 75 images from a training set, and then is tested by 102 images from a testing set. The results show that it is a very effective identification method which can obtain a higher recognition rate.
[1]
Robert G. Harrison,et al.
Wavelet-based detection of coherent structures and self-affinity in financial data
,
2001
.
[2]
George Loizou,et al.
Computer vision and pattern recognition
,
2007,
Int. J. Comput. Math..
[3]
B. Ripley,et al.
Pattern Recognition
,
1968,
Nature.
[4]
Pushpak Bhattacharyya,et al.
Application of a Steerable Wavelet Transform using Neural Network for Signature Verification
,
1999,
Pattern Analysis & Applications.
[5]
Fulei Chu,et al.
FEATURE EXTRACTION OF THE RUB-IMPACT ROTOR SYSTEM BY MEANS OF WAVELET ANALYSIS
,
2003
.