SBIR Phase I: Computerized Algal Identification System (CAIS)

SBIR 第一阶段：计算机化藻类识别系统（CAIS）

• 批准号: 9660769
• 负责人: Ann St. Amand
• 金额: $ 7.5万
• 依托单位: PHYCOTECH INC
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1997
• 资助国家: 美国
• 起止时间: 1997-01-01 至 1997-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9660769&HistoricalAwards=false
• 关键词: SBIR; Phase; Computerized; Algal; Identification

*** 9660769 St. Amand This Small Business Innovation Research Phase I project will implement a novel Computerized Algal Identification System (CAIS) to automatically identify, measure and enumerate algal taxa. Algae are sensitive indicators of stress in our national waters, yet algal data is difficult and expensive to obtain. Producing reliable data requires experienced technicians to spend hours per sample with results varying widely due to differences in methodology and training. The approach for this project unites an experienced algal ecologist with experts in image analysis to build a system initially capable of differentiating 11 genera. CAIS will incorporate automated microscopy and image analysis to analyze cell shape, color (pigment), texture (cell content) and size. Permanently mounted samples provide physical archives, solve orientation problems and retain characteristics necessary for identification and enumeration. Digital image and data archives enable process monitoring, strict classification accountability, and interactive expert evaluation. CAIS will significantly reduce processing time over current methods and ultimately increase laboratory capacities while decreasing measurement costs, and thus overcoming existing cost barriers to algal monitoring. CAIS is versatile and extensible to other taxonomic groups as well. Universities, government agencies, municipalities and consulting firms comprise a market conservatively estimated to generate over two million samples annually. ***

这个小企业创新研究的第一阶段项目将实现一个新的计算机化藻类识别系统（CAIS）来自动识别、测量和枚举藻类分类群。藻类是我们国家水域压力的敏感指标，但藻类数据很难获得且昂贵。产生可靠的数据需要经验丰富的技术人员在每个样本上花费数小时，由于方法和培训的差异，结果差异很大。该项目的方法将一位经验丰富的藻类生态学家与图像分析专家联合起来，建立一个初步能够区分11个属的系统。CAIS将结合自动显微镜和图像分析来分析细胞形状、颜色（色素）、纹理（细胞含量）和大小。永久安装的样品提供了物理档案，解决了定向问题，并保留了识别和枚举所需的特征。数字图像和数据档案可以实现过程监控、严格的分类责任和交互式专家评估。CAIS将大大缩短当前方法的处理时间，并最终提高实验室能力，同时降低测量成本，从而克服现有的藻类监测成本障碍。CAIS是通用的，也可扩展到其他分类组。据保守估计，大学、政府机构、市政当局和咨询公司构成了一个每年产生200多万个样本的市场。＊＊＊