Pork Tissue Recognition Using Visible and Near Infrared Hyperspectral Imaging

Autor: Hu Po-Chi, Liu Zong-Hsin, Tsai Yuan-Hsun, Keng-Hao Liu, Chih-Cheng Pai, Yang-Chu Chen
Rok vydání: 2020
Předmět:
Zdroj: ICS
DOI: 10.1109/ics51289.2020.00084
Popis: Hyperspectral imaging (HSI) has become one of the representative imaging technologies in 21st century. It is widely used in many fields such as geography, ecology, chemistry, medical imaging, and military defense, and so on. In this paper, we utilize HSI technology to collect the spectral data of the specific tissues of pork, observe the spectral characteristics, and attempt to classify the entire pork image by using the collected spectra. We collect the HSI images of pork tissues by using a 470-900nm VNIR hyperspectral camera and a 900-1700nm NIR one. The experiments show that different tissues (e.g., muscles, ligaments, arteries, veins, etc) have different spectral features in certain band regions, and thus could be detected with simple algorithms. Such discovery will help develop a surgery system that combines HSI technology to identify the target tissue and reduce the risk of accidentally injuring important tissues or organs.
Databáze: OpenAIRE