Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Long Distance Non-Contact Dermoscopy: Technological Foundations, Clinical Applications, and Future Directions.

International journal of dermatology·2026

Same author

High-resolution imaging system for integration into intelligent noncontact total body scanner.

Journal of biomedical optics·2025

Same author

Automatic Skin Cancer Detection Using Clinical Images: A Comprehensive Review.

Life (Basel, Switzerland)·2023

Same author

Collision Detection and Avoidance for Underwater Vehicles Using Omnidirectional Vision.

Sensors (Basel, Switzerland)·2022

Search research articles

相关实验视频

Updated: Jan 10, 2026

Hand-held Clinical Photoacoustic Imaging System for Real-time Non-invasive Small Animal Imaging

Hand-held Clinical Photoacoustic Imaging System for Real-time Non-invasive Small Animal Imaging

Published on: October 16, 2017

超光谱成像用于识别猪腹上的异物.

Gabriela Ghimpeteanu¹, Hayat Rajani², Josep Quintana¹

¹Coronis Computing SL, 17003 Girona, Spain.

Sensors (Basel, Switzerland)

|November 27, 2025

概括

此摘要是机器生成的。

超光谱成像 (HSI) 有效地检测到猪肉中的异物,提高了食品安全. 这种自动化质量控制方法显示出高精度和效率,即使温度变化.

关键词:

食品加工行业食品加工行业异物检测异物检测超光谱成像技术的使用.图像分割图像细分图像细分机器学习是机器学习.视觉变压器视觉变压器

更多相关视频

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping

Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping

Published on: December 8, 2015

相关实验视频

Last Updated: Jan 10, 2026

Hand-held Clinical Photoacoustic Imaging System for Real-time Non-invasive Small Animal Imaging

Hand-held Clinical Photoacoustic Imaging System for Real-time Non-invasive Small Animal Imaging

Published on: October 16, 2017

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping

Identification of Metal Oxide Nanoparticles in Histological Samples by Enhanced Darkfield Microscopy and Hyperspectral Mapping

Published on: December 8, 2015

科学领域:

食品科学与技术食品科学与技术
频谱学是一种光谱学.
计算机视觉计算机视觉

背景情况:

食品安全和加工行业的质量控制面临着污染物检测的挑战.
传统的视觉检查方法往往无法识别微妙的污染物.

研究的目的:

评估超光谱成像 (HSI) 的可行性,以检测猪腹肉上的异物.
开发一个用于食品加工实时质量控制的自动化系统.

主要方法:

使用 Specim FX17 超光谱摄像头在 900-1700 nm 范围内获取数据.
采用轻量级视觉变压器实现了细分方法,并进行了预处理和后处理.
在带有和没有污染物的图像上测试了系统,包括在不同的生产线温度下.

主要成果:

该方法实现了高检测准确度,保留了大多数正确的结果,并消除了清洁图像上的错误结果.
该系统证明了对噪声,温度偏移 (10-55°C) 和光谱相似性的强度.
在具有脂肪样光谱的95张图像的挑战性组中观察到零假阳性.

结论:

超光谱成像是一种可行的技术,用于在猪肉加工中自动检测污染物.
开发的基于视觉变压器的方法提供了高精度和训练效率.
该HSI系统支持实时质量控制,大大提高了食品安全保证.