Automatic Classification of Nanoplankton Using a Neural Network on Color Fluorescence Microscope ImagesX&a1r0C

虽然彩色图像分析显微镜最近取得了重大进展，但仍然需要熟练的显微镜专家进行大量干预，才能对细胞类型进行视觉分类。一种准确、快速的分类方法可以显著提高彩色图像分析荧光显微镜估计浮游生物细胞大小和生物量的自动化程度，并可能有利于环境管理人员和关注沿海和河口水域质量的政策制定者。这个项目将研究一种模仿人类视觉分类的自动分类技术。将训练一个关于彩色图像特征的多层感知神经网络来实时执行该分类。图像数据将从河口、海岸和海洋环境的全水浮游生物样本中获得，这些样本是使用图像分析荧光显微镜的标准技术制备的。

While significant progress has been made recently in color image- analyzed microscopy, considerable intervention by a skilled microscopist is still required for visual classification of cell types. An accurate, rapid classification method could significantly improve the automation of color image-analyzed fluorescence microscopy for estimating plankton cell size and biomass and could benefit environmental managers and policy makers concerned with the quality of coastal and estuarine waters. This project will investigate an automatic classification technique which mimics human visual classification. A multilayered perception neural network on color image features will be trained to perform this classification in real time. The image data will be obtained from whole water plankton samples from estuarine, coastal and oceanic environments which have been prepared using standard techniques in image analyzed fluorescence microscopy.