Title :
Automatic Identification of Round Diatom
Author :
Luo, Qiaoqi ; Gao, Yahui ; Luo, Jinfei ; Chen, Changping ; Liang, Junrong ; Yang, Chenhui
Author_Institution :
Sch. of Life Sci., Xiamen Univ., Xiamen, China
Abstract :
In this work, a method for automatic identification of round diatoms based on image texture features is presented. This method combines segmentation adjustment by curve fitting and texture measures based on the spectrum features. The classification accuracy was tested using leave on out methods. With classification carried out using a BP neural network we attained 96.2% accuracy from a set of image containing six species of round diatom. The result is an effective attempt of round diatom identification based on texture character.
Keywords :
backpropagation; curve fitting; ecology; feature extraction; image segmentation; image texture; neural nets; BP neural network; curve fitting; image texture features; leave-on-out methods; round diatom identification; segmentation adjustment; spectrum features; texture measurement; Algae; Curve fitting; Ecosystems; Feature extraction; Image segmentation; Least squares methods; Optical microscopy; Pattern recognition; Robustness; Sea measurements;
Conference_Titel :
Biomedical Engineering and Computer Science (ICBECS), 2010 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5315-3
DOI :
10.1109/ICBECS.2010.5462485
