3D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification Technology

To address the problem of large reconstruction errors in 3D pulse signals caused by excessively small out-of-plane displacement of the contact membrane in the existing traditional Chinese medicine fingertip tactile binocular vision detection technology, this study proposes a 3D pulse image detection...

Full description

Saved in:
Bibliographic Details
Main Authors: Chongyang YAO, Yongxin CHOU, Zhiwei LIANG, Haiping YANG, Jicheng LIU, Dongmei LIN
Format: Article
Language:zho
Published: Editorial Office of Chinese Journal of Medical Instrumentation 2025-05-01
Series:Zhongguo yiliao qixie zazhi
Subjects:
Online Access:https://zgylqxzz.xml-journal.net/article/doi/10.12455/j.issn.1671-7104.240567
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849329299389153280
author Chongyang YAO
Yongxin CHOU
Zhiwei LIANG
Haiping YANG
Jicheng LIU
Dongmei LIN
author_facet Chongyang YAO
Yongxin CHOU
Zhiwei LIANG
Haiping YANG
Jicheng LIU
Dongmei LIN
author_sort Chongyang YAO
collection DOAJ
description To address the problem of large reconstruction errors in 3D pulse signals caused by excessively small out-of-plane displacement of the contact membrane in the existing traditional Chinese medicine fingertip tactile binocular vision detection technology, this study proposes a 3D pulse image detection method based on subtle motion magnification technology and explores its application in pulse pattern recognition. Firstly, a 3D pulse image detection system based on binocular vision to obtain pulse image signals is developed as experimental data. Then, the phase motion video magnification algorithm is used to amplify the original signals, and the amplified signals are reconstructed in three dimensions to obtain 3D pulse signals. On this basis, nine features are extracted from the 3D pulse signals and features selection is performed using a two-sample Kolmogorov-Smirnov test. Finally, machine learning algorithms such as decision trees and random forests are used to identify the five types of pulse conditions: deep pulse, intermittent pulse, flooding pulse, slippery pulse, and rapid pulse. The experimental results show that compared to the methods without subtle motion magnification technology, the proposed method significantly improves waveform clarity, amplitude stability, and periodic regularity. Meanwhile, the average accuracy in pulse pattern recognition reaches 96.29%±0.26%.
format Article
id doaj-art-9d5ac1d3f4da43c49c3536f11e26991b
institution Kabale University
issn 1671-7104
language zho
publishDate 2025-05-01
publisher Editorial Office of Chinese Journal of Medical Instrumentation
record_format Article
series Zhongguo yiliao qixie zazhi
spelling doaj-art-9d5ac1d3f4da43c49c3536f11e26991b2025-08-20T03:47:19ZzhoEditorial Office of Chinese Journal of Medical InstrumentationZhongguo yiliao qixie zazhi1671-71042025-05-0149325526210.12455/j.issn.1671-7104.2405672024-05673D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification TechnologyChongyang YAO0Yongxin CHOU1Zhiwei LIANG2Haiping YANG3Jicheng LIU4Dongmei LIN5Yancheng Institute of Technology, Yancheng, 224007Suzhou University of Technology, Suzhou, 215500Yancheng Institute of Technology, Yancheng, 224007Suzhou University of Technology, Suzhou, 215500Suzhou University of Technology, Suzhou, 215500Lanzhou University of Technology, Lanzhou, 730050To address the problem of large reconstruction errors in 3D pulse signals caused by excessively small out-of-plane displacement of the contact membrane in the existing traditional Chinese medicine fingertip tactile binocular vision detection technology, this study proposes a 3D pulse image detection method based on subtle motion magnification technology and explores its application in pulse pattern recognition. Firstly, a 3D pulse image detection system based on binocular vision to obtain pulse image signals is developed as experimental data. Then, the phase motion video magnification algorithm is used to amplify the original signals, and the amplified signals are reconstructed in three dimensions to obtain 3D pulse signals. On this basis, nine features are extracted from the 3D pulse signals and features selection is performed using a two-sample Kolmogorov-Smirnov test. Finally, machine learning algorithms such as decision trees and random forests are used to identify the five types of pulse conditions: deep pulse, intermittent pulse, flooding pulse, slippery pulse, and rapid pulse. The experimental results show that compared to the methods without subtle motion magnification technology, the proposed method significantly improves waveform clarity, amplitude stability, and periodic regularity. Meanwhile, the average accuracy in pulse pattern recognition reaches 96.29%±0.26%.https://zgylqxzz.xml-journal.net/article/doi/10.12455/j.issn.1671-7104.240567pulse detectionbinocular vision reconstructionpulse pattern recognitionmachine learning
spellingShingle Chongyang YAO
Yongxin CHOU
Zhiwei LIANG
Haiping YANG
Jicheng LIU
Dongmei LIN
3D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification Technology
Zhongguo yiliao qixie zazhi
pulse detection
binocular vision reconstruction
pulse pattern recognition
machine learning
title 3D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification Technology
title_full 3D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification Technology
title_fullStr 3D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification Technology
title_full_unstemmed 3D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification Technology
title_short 3D Pulse Image Detection and Pulse Pattern Recognition Based on Subtle Motion Magnification Technology
title_sort 3d pulse image detection and pulse pattern recognition based on subtle motion magnification technology
topic pulse detection
binocular vision reconstruction
pulse pattern recognition
machine learning
url https://zgylqxzz.xml-journal.net/article/doi/10.12455/j.issn.1671-7104.240567
work_keys_str_mv AT chongyangyao 3dpulseimagedetectionandpulsepatternrecognitionbasedonsubtlemotionmagnificationtechnology
AT yongxinchou 3dpulseimagedetectionandpulsepatternrecognitionbasedonsubtlemotionmagnificationtechnology
AT zhiweiliang 3dpulseimagedetectionandpulsepatternrecognitionbasedonsubtlemotionmagnificationtechnology
AT haipingyang 3dpulseimagedetectionandpulsepatternrecognitionbasedonsubtlemotionmagnificationtechnology
AT jichengliu 3dpulseimagedetectionandpulsepatternrecognitionbasedonsubtlemotionmagnificationtechnology
AT dongmeilin 3dpulseimagedetectionandpulsepatternrecognitionbasedonsubtlemotionmagnificationtechnology