Ginoris Y P, Amaral A L, Nicolau A, Coelho M A Z, Ferreira E C
Departamento de Engenharia Bio química, Escola de Química/UFRJ, Centro de Tecnologia, E-113, Cidade Universitária, Ilha do Fundão, Rio de Janeiro, CEP: 21941-900, Brazil.
Water Res. 2007 Jun;41(12):2581-9. doi: 10.1016/j.watres.2007.02.006. Epub 2007 Mar 30.
A procedure for the semi-automatic identification of the main protozoa and metazoa species present in the activated sludge of wastewater treatment plants was developed. This procedure was based on both image processing and multivariable statistical methodologies, leading to the use of the image analysis morphological descriptors by discriminant analysis and neural network techniques. The image analysis program written in Matlab has proved to be adequate in terms of protozoa and metazoa recognition, as well as for the operating conditions assessment.
开发了一种用于半自动识别污水处理厂活性污泥中主要原生动物和后生动物物种的程序。该程序基于图像处理和多变量统计方法，通过判别分析和神经网络技术使用图像分析形态学描述符。用Matlab编写的图像分析程序已证明在原生动物和后生动物识别以及运行条件评估方面是足够的。
