Laser & Optoelectronics Progress, Volume. 56, Issue 1, 011101(2019)
Myocardial Ischemia Pre-Diagnosis Method Based on Infrared Thermal Imaging and BP Neural Network
Figures & Tables(10)
Fig. 2. Process of myocardial ischemic pre-diagnosis based on infrared imaging data
Fig. 3. Neck and shoulder positioning process is performed by template matching method
Fig. 7. Core size 3×3 different convolution kernel operation results. (a) Original image; (b) Sobel operator processed; (c) Laplace operator processed; (d) Gaussian operator processed
Fig. 8. Core size 5×5 different convolution kernel operation results. (a) Original image; (b) Sobel operator processed; (c) Laplace operator processed; (d) Gaussian operator processed
Table 1. Accuracy of different convolution experiments in BP neural network classifier test set
View tableTable 1. Accuracy of different convolution experiments in BP neural network classifier test set
Nuclear size Sobel operator /% Gaussian core /% Laplace operator /% 3×3 77.78 95.56 73.33 5×5 75.56 91.11 66.67
Tools
Get Citation
Copy Citation Text
Baohong Mi, Wenxue Hong, Jialin Song, Shiming Wu, Hui Meng. Myocardial Ischemia Pre-Diagnosis Method Based on Infrared Thermal Imaging and BP Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(1): 011101
Paper Information
Category: Imaging Systems
Received: Sep. 3, 2018
Accepted: Sep. 27, 2018
Published Online: Aug. 1, 2019
The Author Email: Wenxue Hong (hongwx@ysu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20