開發瘀傷溯源之單照式光譜影像及分析系統

Project Details

Description

According to the Ministry of Health and Welfare, the number of reported cases ofchild abuse is around 40,000 each year from 2019 to 2021. Although bruises canbe found on the victim's body by first-line personnel during treatment, the lack ofconvenient and objective detection techniques often prevents the acquisition ofevidence of abuse and domestic violence, which reduces the defensive capabilityof the first line. In this study, we will construct a snapshot bruise spectral imagingand analysis system. Compared to conventional spectral imaging systems thatrequire a relatively complete spectrum (containing tens to hundreds of spectraldimensions), this system uses principal component analysis to identify thecharacteristic spectra (containing only 2-3 principal components) in the diffusereflectance spectrum of bruised skin, and through the design of the filter andcamera imaging, the distribution of the content of different principal componentsin the bruise area can be obtained in a single image. After obtaining the contentinformation of the principal components, the distribution of the pigmentcomposition in the bruise area can be analyzed and the time of bruise formationcan be quickly estimated. In order to reasonably reduce the spectral dimension,obtain the correct pigment molecular composition, and analyze the bruiseformation time, the principal component spectrum of the bruise is identified byprincipal component analysis (PCA) during the system development process, andthe time variation between the principal component spectrum content and thebruise progression is modeled by machine learning algorithm. Finally, we designthe filter with the principal component spectra, develop the reconstructionalgorithm of the principal component spectral content image, and develop asnapshot spectral imaging system for bruise detection through the lens design.After the system is developed, it will provide an objective way to assist in theidentification of domestic violence, child abuse, or cause of death, which willhopefully increase the country's ability to prevent and treat such criminal cases.In addition, the snapshot system based on principal component spectroscopyprovides a new type of spectral imaging technology that can be further applied toother fields such as agricultural technology, environmental testing, biomedicalresearch, food science, etc., providing a simpler and more real-time detectiontool.
StatusFinished
Effective start/end date1/08/2331/10/24

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 8 - Decent Work and Economic Growth
  • SDG 9 - Industry, Innovation, and Infrastructure
  • SDG 17 - Partnerships for the Goals

Keywords

  • Bruise
  • diffuse reflection spectrum
  • principal component analysis
  • photoacoustic image
  • spectral image

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.