Viability prediction of Ricinus cummunis L. seeds using multispectral imaging.

Merete Olesen,Lise Deleuran,Santosh Shrestha,Pejman Nikneshan,Birte Boelt,René Gislum,Ali Tadayyon

doi:10.3390/s150204592

Merete Olesen, Lise Deleuran + Show 5 more

Open Access

https://doi.org/10.3390/s150204592

Copy DOI

Abstract

The purpose of this study was to highlight the use of multispectral imaging in seed quality testing of castor seeds. Visually, 120 seeds were divided into three classes: yellow, grey and black seeds. Thereafter, images at 19 different wavelengths ranging from 375–970 nm were captured of all the seeds. Mean intensity for each single seed was extracted from the images, and a significant difference between the three colour classes was observed, with the best separation in the near-infrared wavelengths. A specified feature (RegionMSI mean) based on normalized canonical discriminant analysis, were employed and viable seeds were distinguished from dead seeds with 92% accuracy. The same model was tested on a validation set of seeds. These seeds were divided into two groups depending on germination ability, 241 were predicted as viable and expected to germinate and 59 were predicted as dead or non-germinated seeds. This validation of the model resulted in 96% correct classification of the seeds. The results illustrate how multispectral imaging technology can be employed for prediction of viable castor seeds, based on seed coat colour.

Highlights

Castor (Ricinus communis L.) is a significant non-edible oil crop, considered a vital industrial raw material
To our knowledge this is the first study on castor, where the seed coat colour reflection has been measured using multispectral imaging and classified in accordance to seed viability
The results suggest that reflection data from the castor seed coat can be valuable in prediction of seed viability

Summary

Introduction

Castor (Ricinus communis L.) is a significant non-edible oil crop, considered a vital industrial raw material. It is cultivated on 1.5 mio hectares worldwide with an annual seed production of 1.85 Mt and an average seed yield of 1235 kg·ha−1 [1]. Castor can be grown on marginal lands not suitable for food crops. These features combined make castor an attractive alternative biodiesel feedstock. Seed quality is very important to optimize plant growth and yield production on farms. Rapid and uniform germination and subsequent seedling development and crop establishment are important factors influencing yield potential as the plant has limited ability to compensate for low plant densities [2,3]

Objectives

Results

Conclusion