SpectraSeed

Innovation project with the aim of developing multispectral technology for fast, cost-efficient, and non-destructive analysis of seed quality. 

AU, Videometer and Danish seed industry 

Multispectral imaging

Illumination with 19 specific wavelengths (375-970 nm)

Picture at each wavelength

Identify obejct/or part of it based on their reflection spectrum

Castor Bean (Ricinus communis L.)

Visit of PhD student Pejman Nikneshan from Iran

Castor bean is a non-edible oil crop produced on 1.5 million hectares worldwide

Goal: Evaluate non-destructive analysis techniques for seed quality sorting (single seed NIR and VideometerLab)

Published: Sensor

Castor  Bean (Ricinus communis L.)

Supervised model

Calibration set (120 seeds from harvest 2013) 

Determine whether the spectral units can be correlated with (and predict) the viability of the individual seed. 

Mark area of interest: viable seed is painted green and dead seed is painted red.

Normalized canonical discriminant analysis (nCDA) is done and a trimmed mean of

the pixel intensity values for each single seed is calculated (RegionMSImean).

The treshold value was set to zero, so negative values correlate for viable seeds and positive values correlate for dead seeds.Supervised model

Calibration set (120 seeds from harvest 2013) :

Determine whether the spectral units can be correlated with (and predict) the viability of the individual seed. 

Mark area of interest: viable seed is painted green and dead seed is painted red.

Normalized canonical discriminant analysis (nCDA) is done and a trimmed mean of

the pixel intensity values for each single seed is calculated (RegionMSImean).

The treshold value was set to zero, so negative values correlate for viable seeds and positive values correlate for dead seeds.

Validation set (300 seeds from harvest 2013)    

    Test if the value of the spectral units actually predict viable seeds and thereby are valuable in determination of germination capacity

Conclusions/future perspectives

    Reflection data from the castor seed coat are valuable in prediction of seed viability

    Multispectral imaging is a good non-destructive technology for seed quality sorting of castor

bean

    This study could be of interest to try on other crops, where the seeds mature sequentially and thereby obtain variation in seed coat color. E.g. Brassica species

SpectraSeed 2013-16

   Purity: weed seed species in spinach samples (DanSeed 2014) 

    Seed health: fusarium and other fungi on barley/DNA as reference test 

    Seed germination: grass seed

Germination of Lolium perenne, exsperiment at AU

    Seed material

    Raw seed samples of the cultivar Calibra

    Sorted in 5 fractions on the gravity table

   Samples from fraction 3 and 4 were aged  (22% MC, 45oC hot water, for 48h)

    Seeds were divided into 3 groups (different caryopsis size, relative to the size of the seed unit)

with 4 x 25 seeds of each size

    Images were captured at day zero and once or twice a day during germination

    Seeds are marked by colours in accordance with germination (green) and non-germination

(red)。

Grass seed (Lolium perenne)

    Seed segmentation and collection in a blob database

    Caryopsis length and seed length are measured, and a ratio is calculated

    Radicle length are measured

附：012_Merete_Halkjaer_Olesen_multispectral_image_analysis.pdf