Binary Plankton Image Classification
Authors:
- Xiaoou TangXTXiaoou Tang
- Feng LinFLFeng Lin
- Scott SamsonSSScott Samson
- Andrew RemsenARAndrew Remsen
- 1 July 2006
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 31 (3) , 728-735
Abstract
In marine biology study, it is important to investigate the distribution of plankton organisms. Because of the overwhelming data size, automatic processing of the large amount of image data collected by underwater image recorders becomes inevitable. However, due to the fragmentation and the large within-class variations of binary plankton images, it is difficult to extract reliable shape features. In this paper, we propose several new shape descriptors and use a normalized multilevel dominant eigenvector estimation method to select a best feature set for binary plankton image classification. We achieve more than 91% classification accuracy in experiments on more than 3000 imagesKeywords
This publication has 18 references indexed in Scilit:
- Do experts make mistakes? A comparison of human and machine identification of dinoflagellatesMarine Ecology Progress Series, 2003
- Spatial size distributions: applications to shape and texture analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Directional morphological filteringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- A system for high-resolution zooplankton imagingIEEE Journal of Oceanic Engineering, 2001
- Texture information in run-length matricesIEEE Transactions on Image Processing, 1998
- Representation of 3D surfaces by two-variable Fourier descriptorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- A moment-based unified approach to image feature detectionIEEE Transactions on Image Processing, 1997
- The revised fundamental theorem of moment invariantsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Pattern spectrum and multiscale shape representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989
- On image analysis by the methods of momentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1988