Phenotyping earthworm by image analysis

Date

2014

Authors

Kumar, P.
Matheyarasu, R.
Bolan, N.
Miklavcic, S.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

2014 13th International Conference on Control, Automation, Robotics & Vision (ICARCV), 2014, pp.205-210

Statement of Responsibility

Conference Name

2014 13th International Conference on Control, Automation, Robotics and Vision (10 Dec 2014 - 12 Dec 2014 : Singapore)

Abstract

Non-destructive phenotyping of earthworms by digital imaging and image analysis is the novel concept being proposed and explored in this paper. Earthworms are very important component of plant soil interaction via rhizosphere.Although a lot of research resources have been applied to phenotying roots by image analysis, there has been practically insignificant work on phenotying earthworms by image analysis.We put together some tailor made image analysis techniques(segmentation, medial axis thinning) along with a mathematical model for earthworms, to compute the volume, surface areaand length of earthworms. We developed a novel radius versus length plot to identify the mouth-end, clitellum, and anus-endof earthworms by machine vision. We then compare the results of the phenotyping measurement obtained by our approach to those of the intercept principle. Intercept principle has been commonly used for phenotyping roots. Further more we proposea novel colour signature for blobs obtained by segmenting earthworms for colour analysis of the earthworms. It is expected that the colour information of earthworms can give clues on bioavailability of nutrients in soil or/and for earthworm species recognition. Both by qualitative and quantitative analysis we show that the segmentation and phenotype computation are better than the conventional approach of intercept principle.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright 2014 IEEE

License

Grant ID

Call number

Persistent link to this record