Collaborative Research: Rapid Digital Specimen Image and Data Capture: A Web Services Solution

建议#DBI-BDI：0345387 PI：Heidorn摘要伊利诺伊大学与耶鲁大学和纽约植物园合作，获得了一项拨款，用于创建一个系统，对自然历史标本(本例中为植物标本)中的标本进行图像处理，使用光学字符识别、自然手写识别和自然语言处理来读取标本上的标签，并将标签数据解析到其组成部分字段中，然后将数据输入数据库。模块化、可配置、开放源码的Web服务将在镜像的分布式环境中提供互操作性和可伸缩性。该项目将使自然历史收集的数据采集更有效率，并降低每个数字化标本的相关时间和成本。

Proposal # DBI-BDI: 0345387 PI: Heidorn AbstractThe University of Illinois has been awarded a grant in collaboration with Yale University and the New York Botanical Garden to create a system to image specimens in natural history collections (plant specimens in this case), use Optical Character Recognition (OCR), Natural Handwriting Recognition (NHR) and Natural Language Processing (NLP) to read the labels on the specimens and parse the label data into its component fields, then enter the data into a database. Modular, configurable, open source web services will provide interoperability and scalability in mirrored, distributed environments. This project will make the data capture of natural history collections much more efficient and lower the associated time and costs per specimen digitized.