Stitching defect detection and classification using wavelet transform and BP neural network

2009 ◽  
Vol 36 (2) ◽  
pp. 3845-3856 ◽  
Author(s):  
W.K. Wong ◽  
C.W.M. Yuen ◽  
D.D. Fan ◽  
L.K. Chan ◽  
E.H.K. Fung
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Defect Detection ◽  
Bp Neural Network

scholarly journals Motor Fault Detection Using Wavelet Transform and Improved PSO-BP Neural Network

Processes ◽  
2020 ◽  
Vol 8 (10) ◽  
pp. 1322 ◽  
Author(s):  
Chun-Yao Lee ◽  
Yi-Hsin Cheng
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Fault Detection ◽  
Bp Neural Network ◽  
Short Circuit ◽  
Back Propagation ◽  
Operating Environment ◽  
Cause Of Failure ◽  
Bearing Damage ◽  
Improved Pso

This paper proposes a motor fault detection method based on wavelet transform (WT) and improved PSO-BP neural network which is combined with improved particle swarm optimization (PSO) and a back propagation (BP) neural network with linearly increasing inertia weight. First, this research used WT to analyze the current signals of the healthy motor, bearing damage motor, stator winding inter-turn short circuit motor, and broken rotor bar motor. Second, features after completing the signal analysis were extracted, and three types of classifiers were used to classify. The results show that the improved PSO-BP neural network can effectively detect the cause of failure. In addition, in order to simulate the actual operating environment of the motor, this study added white noise with signal noise ratios of 30 dB, 25 dB, and 20 dB to verify that this model has a better anti-noise ability.

scholarly journals A Hybrid Method of Face Detection Based on Feature Optimization and Neural Network

2019 ◽  
Vol 8 (4) ◽  
pp. 8998-9002
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Face Detection ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Discrete Wavelet ◽  
Facial Image ◽  
Feature Optimization ◽  
Bp Neural Network Model

The advancement of digital technology needs biometric security systems. Face detection plays an essential role in the security of digital devices. The detection of a face based on the lower content of the facial image for the processing of detection. In this paper modified the BP Neural Network Model for the detection of the human face. The modification of face detection algorithms incorporates feature optimization. The feature optimization process reduces the distorted features of the facial image. The optimized features of facial image enhance the performance of face detection for the optimization of features used glowworm optimization algorithms. The glowworm optimization algorithm is a dynamic population-based search technique. The concept of glowworm is a neighbor’s selection of worms based on the process of lubrification. For feature extraction we use discrete wavelet transform. The discrete wavelet transform function drives the features component in terms of low frequency and high frequency of facial image. The proposed algorithm simulated in MATLAB software and used a reputed facial image dataset from CSV300. Our experimental results show a better detection rate instead of the BP neural network model.

Application of the Compound Model of BP Neural Networks and Wavelet Transform in Image Definition Identification

2012 ◽  
Vol 605-607 ◽  
pp. 2265-2269
Author(s):  
Rui Kun Gong ◽  
Ya Nan Zhang ◽  
Chong Hao Wang ◽  
Li Jing Zhao
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Bp Neural Network ◽  
Wavelet Transformation ◽  
Recognition Rate ◽  
Discrete Wavelet ◽  
Training Set ◽  
Identification Method ◽  
Compound Model ◽  
Image Definition

First, the background, significance and general implementation of the image definition identification are introduced. Then, basic theory of wavelet transform and neural network is expounded. An identification method of image definition based on the composite model of wavelet analysis and neural network is suggested．The two—dimensional discrete wavelet transformation is used to filter image signal and extract its brim character which is input into BP neural network for identification. 4 layers of BP neural network are constructed to perform image definition identification. The compound model is first trained by 90 images from the training set, and then is tested by 87 images from the testing set. The results show that this is a very effective identification method which can obtain a higher recognition rate.

Sign in / Sign up

Export Citation Format

Share Document