相关实验视频
Updated: Jan 15, 2026

Fruit Volatile Analysis Using an Electronic Nose
Published on: March 30, 2012
多任务NoisyViT用于增强水果和蔬菜新鲜度检测和类型分类
Siavash Esfandiari Fard1, Tonmoy Ghosh1, Edward Sazonov1
1Department of Electrical and Computer Engineering, The University of Alabama, Tuscaloosa, AL 35401, USA.
一个新的多任务噪音视觉变压器 (NoisyViT) 模型使用图像准确地检测水果和蔬菜的新鲜度. 这种人工智能方法为供应链和零售业的自动化质量评估提供了可扩展的解决方案.
科学领域:
- 计算机视觉和人工智能的人工智能
- 农业技术 农业技术
- 食品科学与技术 食品科学与技术
背景情况:
- 水果和蔬菜的新鲜度对于质量,营养和减少浪费至关重要,需要准确的评估方法.
- 传统的手动质量评估是主观和低效的,推动了对自动化解决方案的需求.
- 图像传感器与人工智能 (AI) 结合,为客观和可扩展的质量监测提供了有希望的途径.
研究的目的:
- 评估噪音视觉变压器 (NoisyViT) 模型在自动检测图像上的水果和蔬菜新鲜度方面的有效性.
- 开发和评估一个多任务NoisyViT模型,同时进行新鲜度和类型分类,增强概括性.
- 建立一个强大的和可扩展的AI解决方案,用于在整个食品供应链中实时进行质量评估.
主要方法:
- NoisyViT模型最初在五个公共数据集上进行了测试,实现了新鲜度检测的高精度.
- 通过合并五个数据集,创建了一个统一的数据集,Freshness44,包括22种水果和蔬菜类型的44个类别.
- 噪音ViT架构被调整为多任务配置,用于新鲜度 (二进制) 和类型 (22-类) 识别的分离分类头,在Freshness44.4上进行微调.
主要成果:
- 单头NoisyViT模型在单个数据集上显示出高精度 (超过97%).
- 多任务NoisyViT模型在Freshness44数据集上实现了99.60%的新鲜度检测和99.86%的类型分类的特殊准确性.
- 多任务模型在分类准确性方面超过了单头NoisyViT和传统的机器学习/CNN方法.
结论:
- 在全面的Freshness44数据集上训练的多任务NoisyViT模型提供了一个高度有效和准确的解决方案,用于自动检测水果和蔬菜的新鲜度.
- 这种由人工智能驱动的方法提供了一个可扩展和强大的实时质量监测系统,适用于供应链,零售和消费者环境.
- 该研究强调了先进的人工智能架构 (如NoisyViT) 的潜力,以应对食品质量评估和废物减少方面的关键挑战.
更多相关视频
04:21Author Spotlight: Sieving Fruit Pulp to Detect Immature Tephritid Fruit Flies in the Field
Published on: July 28, 2023
08:43PTR-ToF-MS Coupled with an Automated Sampling System and Tailored Data Analysis for Food Studies: Bioprocess Monitoring, Screening and Nose-space Analysis
Published on: May 11, 2017
相关概念视频
Fruit Development, Structure, and Function
Methods of Classification and Identification
Force Classification
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Sample Handling
Samples should be transported carefully from collection points to the laboratory. They should be properly sealed and clearly labeled to prevent cross-contamination. To preserve the sample integrity, optimal temperature conditions during transport are essential. This could involve using...
Classification of Signals
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
Extraction: Advanced Methods