Development of Automated Image Analysis Software for Suspended Marine Particle Classification.

摘要

The goal of this project is to develop a broadly-capable software package, to automatically classify digital images of zooplankton. The software is being developed initially for classification of images from the SIPPER linescan imaging instrument, but will also be able to process images from imaging systems that produce high quality digital image. Towards this end, the software is being created to include both training and multi-stage classification portions. The input is digital images in standard computer format. The output is an Internet-addressable classified particle database, including pertinent particle hydrographic information and sorted images. The project has application in rapid classification of microscopic marine particles, which have an effect on the optical properties and long-term variation in the local and global water column.