I-Corps: Interactive Software for Hyperspectral Image Analysis

I-Corps：用于高光谱图像分析的交互式软件

• 批准号: 2138150
• 负责人: Mikhail Berezin
• 金额: $ 5万
• 依托单位: Washington University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-15 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2138150&HistoricalAwards=false
• 关键词: Corps; Interactive; Software; Hyperspectral; Image

The broader impact/commercial potential of this I-Corps project is to simplify the workflow, reduce analysis time, and enable deep searching capabilities across hyperspectral datasets using a new computational platform. Hyperspectral imaging, or chemical imaging, is the combination of spectroscopy and digital imaging. The proposed system incorporates advanced imaging and machine learning algorithms to streamline data processing and enable users to focus on the application itself, rather than spending time and money on developing image processing algorithms. Hyperspectral imaging is broadly used to diagnose diseases and measure a patient's response to therapy, to enhance product quality by enabling optical sorters to identify and remove defective products, and to identify minerals from drill cores and remote sensing. A potential early application for the software platform will be in agriculture to identify early stress in crops, assess soil health, quantify water resources, and predict harvest yields.This I-Corps project further develops a software platform for deep mining of data derived from hyperspectral imaging. The system performs several essential operations in the spectral imaging domain and enables advanced image analysis for users across a range of technical proficiencies. The strength of the proposed software lies in its intuitive design that enables the user to perform high level data analysis from image processing to machine learning via a visual, interactive interface. Built around a collection of current and proprietary spectral imaging algorithms, the software facilitates the search of hidden information inside large datasets, providing broad improvements in data analysis. The package can be operated without prior programming skills and allows most currently used data formats to be processed in real time. The interactivity, object identification, and machine learning algorithms enable high efficiency during analysis of hyperspectral images.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该I-Corps项目的更广泛的影响/商业潜力是简化工作流程，减少分析时间并使用新的计算平台在高光谱数据集中进行深度搜索功能。高光谱成像或化学成像是光谱和数字成像的组合。 提出的系统结合了高级成像和机器学习算法来简化数据处理，并使用户能够专注于应用程序本身，而不是花费时间和金钱来开发图像处理算法。高光谱成像广泛用于诊断疾病并测量患者对治疗的反应，从而通过使光学分子能够识别和去除有缺陷的产品，并从钻芯和遥感中识别矿物质来提高产品质量。 软件平台的潜在早期应用将是农业，以确定农作物的早期压力，评估土壤健康，量化水资源并预测收获的收益。这项I-Corps项目进一步开发了一个软件平台，用于深入挖掘从高光谱成像中得出的数据。该系统在光谱成像域中执行多个基本操作，并为各种技术能力的用户提供高级图像分析。所提出的软件的强度在于其直观设计，使用户能够通过视觉，交互式接口进行从图像处理到机器学习的高级数据分析。该软件围绕着当前和专有光谱成像算法的集合而建，该软件促进了对大型数据集中隐藏信息的搜索，从而在数据分析方面提供了广泛的改进。该软件包可以在没有事先编程技能的情况下操作，并允许实时处理大多数当前使用的数据格式。互动性，对象识别和机器学习算法在分析高光谱图像期间可以很高效率。该奖项反映了NSF的法定任务，并且使用基金会的知识分子优点和更广泛的影响评估标准，被认为值得通过评估来提供支持。