<abstract xml:lang="en" xmlns="http://www.w3.org/1999/xhtml"><p>The analysis of plant root system images plays an important role in the diagnosis of plant health state, the detection of possible diseases and growth distortions. This paper describes an initial stage of automatic analysis—the segmentation method for scanned images of Ni-treated wheat roots from hydroponic culture. The main roots of a wheat fibrous system are placed separately in the scanner view area on a high chroma background (blue or red). The first stage of the method includes the transformation of a scanned RGB image into the HCI (Hue-Chroma-Intensity) colour space and then local thresholding of the chroma component to extract a binary root image. Possible chromatic discolourations, different from background colour, are added to the roots from blue or red chroma subcomponent images after thresholding. At the second stage, dark discolourations are extracted by local fuzzy c-means clustering of an HCI intensity image within the binary root mask. Fuzzy clustering is applied in local windows around the series of sample points on roots medial axes (skeleton). The performance of the proposed method is compared with hand-labelled segmentation for a series of several root systems.</p></abstract>

The analysis of plant root system images plays an important role in the diagnosis of plant health state, the detection of possible diseases and growth distortions. This paper describes an initial stage of automatic analysis—the segmentation method for scanned images of Ni-treated wheat roots from hydroponic culture. The main roots of a wheat fibrous system are placed separately in the scanner view area on a high chroma background (blue or red). The first stage of the method includes the transformation of a scanned RGB image into the HCI (Hue-Chroma-Intensity) colour space and then local thresholding of the chroma component to extract a binary root image. Possible chromatic discolourations, different from background colour, are added to the roots from blue or red chroma subcomponent images after thresholding. At the second stage, dark discolourations are extracted by local fuzzy c-means clustering of an HCI intensity image within the binary root mask. Fuzzy clustering is applied in local windows around the series of sample points on roots medial axes (skeleton). The performance of the proposed method is compared with hand-labelled segmentation for a series of several root systems.

An automatic segmentation method for scanned images of wheat root systems with dark discolourations

Computer Engineering Department, Technical University of Łódź, Stefanowskiego 18/22, 90-924 Łódź, Poland

Department of Plant Physiology and Biochemistry, University of Łódź, Banacha 12/16, 90-237 Łódź, Poland

International Journal of Applied Mathematics and Computer Science

The analysis of plant root system images plays an important role in the diagnosis of plant health state, the detection of possible diseases and growth...

An automatic segmentation method for scanned images of wheat root systems with dark discolourations

Published Online: Dec 31, 2009

Page range: 679 - 689

DOI: https://doi.org/10.2478/v10006-009-0055-x

Keywords
root system image, segmentation, skeleton, root discolourations, fuzzy c-means clustering

This content is open access.

An automatic segmentation method for scanned images of wheat root systems with dark discolourations

Published Online: Dec 31, 2009

Page range: 679 - 689

DOI: https://doi.org/10.2478/v10006-009-0055-x

Keywordsroot system image, segmentation, skeleton, root discolourations, fuzzy c-means clustering

This content is open access.

Keywords
root system image, segmentation, skeleton, root discolourations, fuzzy c-means clustering