In early October, a study was published which considered the possibility of using the optical properties of Cavendish bananas, such as absorption, reduced scattering and effective attenuation coefficient, from images captured at five different wavelengths (532, 660, 785, 830, and 1060 nm), to predict the quality characteristics of the fruit.
Researchers considered six different ripening stages - 2= green with a trace of yellow; 3= more green than yellow; 4= more yellow than green; 4= yellow with a trace of green; 6= all yellow; 7= all yellow with brown speckles.
It seems like there is a strong correlation between appearance and ripening stage at 532, 660 and 785 nm.
Absorption and effective attenuation coefficient showed a negative correlation with ripening stages, while scattering showed a positive correlation. Researchers used this data to develop prediction and classification models with an artificial neural network.
The visible wavelength region (532,660 and 785 nm) gave the highest correlation coefficient to predict elasticity, while the near infrared region (830 and 1060 nm) gave the highest correlation coefficient to predict soluble solid content (SSC) when the absorption and reduced scattering coefficients were used.
To classify bananas in the six ripening stages, the maximum classification precision given by visible wavelength was 97.5%.
"This study showed optical properties can be used to predict the quality of bananas and to classify them according to their ripening stage."
Source: Segun Emmanuel Adebayo, Norhashila Hashim, Khalina Abdan, Marsyita Hanafi, Kaveh Mollazade, 'Prediction of quality attributes and ripeness classification of bananas using optical properties', Scientia Horticulturae, Vol. 212, pag. 171–182.
www.sciencedirect.com/science/article/pii/S0304423816304952