Image recognition based on Boltzmann machine algorithm

2021 ◽  
pp. 1-15
Author(s):  
Hao Li
Keyword(s):  
Image Recognition ◽  
Median Filter ◽  
Boltzmann Machine ◽  
Threshold Method ◽  
Recognition Method ◽  
Fuzzy Enhancement ◽  
Recognition Ability ◽  
Mean Filter ◽  
Different Shapes ◽  
Boltzmann Method

Due to the influence of recognition parameters, image recognition has low recognition accuracy, long recognition time and large storage cost. Therefore, an automatic image recognition method based on Boltzmann machine is proposed. Based on threshold method and fuzzy set method, image malformation correction is performed. The mean filter and median filter are combined to eliminate the influence of image filtering, and the pre-processing of image is completed by using the fuzzy enhancement of image. Based on the restricted Boltzmann method, the network model is dynamically evolved, and the identification parameters of each shape and contour are obtained. Different shapes and contours are classified and recognized. Simulation results show that image recognition method based on human-computer interaction has high recognition ability, shortens the time cost and greatly reduces the space needed for node storage.

Machine-Printed Invoice Number Based on Fuzzy Recognition

2012 ◽  
Vol 214 ◽  
pp. 705-710 ◽  
Author(s):  
Xiao Ping Xian
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Recognition Rate ◽  
Real System ◽  
Recognition Method ◽  
Recognition Time ◽  
Recognition Ability ◽  
System Requirements ◽  
Fuzzy Recognition ◽  
Detection And Separation

A new fuzzy recognition method of machine-printed invoice number based on neural network is presented. This method includes ten links: invoice number detection and separation of right on top of invoice, binarization, denoising, incline correction, extraction of invoice code numerals, window scaling, location standardization, thinning, extraction of numeral feature and fuzzy recognition based on BP neural network. Through testing, the recognition rate of this method can be over 99%.The recognition time of characters for character is less than 1 second, which means that the method is of more effective recognition ability and can better satisfy the real system requirements.

One Extended OTSU Flame Image Recognition Method Using RGBL and Stripe Segmentation

2011 ◽  
Vol 121-126 ◽  
pp. 2141-2145 ◽  
Author(s):  
Wei Gang Yan ◽  
Chang Jian Wang ◽  
Jin Guo
Keyword(s):  
Image Segmentation ◽  
Water Vapor ◽  
Image Recognition ◽  
Recognition Accuracy ◽  
New Method ◽  
Recognition Method ◽  
Otsu’S Method ◽  
Flame Shape ◽  
Image Segmentation Algorithm ◽  
Rgb Image

This paper proposes a new image segmentation algorithm to detect the flame image from video in enclosed compartment. In order to avoid the contamination of soot and water vapor, this method first employs the cubic root of four color channels to transform a RGB image to a pseudo-gray one. Then the latter is divided into many small stripes (child images) and OTSU is employed to perform child image segmentation. Lastly, these processed child images are reconstructed into a whole image. A computer program using OpenCV library is developed and the new method is compared with other commonly used methods such as edge detection and normal Otsu’s method. It is found that the new method has better performance in flame image recognition accuracy and can be used to obtain flame shape from experiment video with much noise.

Application of Improved Back Propagation Neural Network for the Recognition of Composite Insulator Hydrophobicity Grade

2013 ◽  
Vol 373-375 ◽  
pp. 1155-1158
Author(s):  
Kang Yan ◽  
Zhong Yuan Zhang
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Median Filter ◽  
Back Propagation ◽  
Histogram Equalization ◽  
Back Propagation Neural Network ◽  
Threshold Method ◽  
Safe Operation ◽  
Composite Insulator ◽  
Adaptive Median Filter

The detection of hydrophobicity is an important way to evaluate the performance of composite insulator, which is helpful to the safe operation of composite insulator. In this paper, the image processing technology and Back Propagation neural network is introduced to recognize the composite insulator hydrophobicity grade. First, hydrophobic image is preprocessed by histogram equalization and adaptive median filter, then the image was segmented by Ostu threshold method, and four features associated with hydrophobicity are extracted. Finally, the improved Back Propagation neural network is adopted to recognize composite insulator hydrophobicity grade. The experimental results show that the improved Back Propagation neural network can accurately recognize the composite insulator hydrophobicity

scholarly journals Design of median-type filters with an impulse noise detector using decision tree and particle swarm optimization for image restoration

2010 ◽  
Vol 7 (4) ◽  
pp. 859-882 ◽  
Author(s):  
Bae-Muu Chang ◽  
Hung-Hsu Tsai ◽  
Xuan-Ping Lin ◽  
Pao-Ta Yu
Keyword(s):  
Particle Swarm Optimization ◽  
Decision Tree ◽  
High Performance ◽  
Impulse Noise ◽  
Median Filter ◽  
Particle Swarm ◽  
Swarm Optimization ◽  
Ordered Median ◽  
Mean Filter ◽  
Hybrid Detector

This paper proposes the median-type filters with an impulse noise detector using the decision tree and the particle swarm optimization, for the recovery of the corrupted gray-level images by impulse noises. It first utilizes an impulse noise detector to determine whether a pixel is corrupted or not. If yes, the filtering component in this method is triggered to filter it. Otherwise, the pixel is kept unchanged. In this work, the impulse noise detector is an adaptive hybrid detector which is constructed by integrating 10 impulse noise detectors based on the decision tree and the particle swarm optimization. Subsequently, the restoring process in this method respectively utilizes the median filter, the rank ordered mean filter, and the progressive noise-free ordered median filter to restore the corrupted pixel. Experimental results demonstrate that this method achieves high performance for detecting and restoring impulse noises, and outperforms the existing well-known methods.

Sign in / Sign up

Export Citation Format

Share Document