Flesh of pumpkin from ecological farming as part of fruit suitable for non-destructive cultivar classification using computer vision

The aim of this study was to build the discriminative models for distinguishing the different cultivars of flesh of pumpkin ‘Bambino’, ‘Butternut’, ‘Uchiki Kuri’ and ‘Orange’ based on selected textures of the outer surface of images of cubes. The novelty of research involved the use of about 2000 different textures for one image. The highest total accuracy (98%) of discrimination of pumpkin ‘Bambino’, ‘Butternut’, ‘Uchiki Kuri’ and ‘Orange’ was determined for models built based on textures selected from the color space Lab and the IBk classifier and some of the individual cultivars were classified with the correctness of 100%. The total accuracy of up to 96% was observed for color space RGB and 97.5% for color space XYZ. In the case of color channels, the total accuracies reached 91% for channel b, 89.5% for channel X, 89% for channel Z.

Morphological, physiological, pests and diseases responses of citrus seedling cultivars, and their contribution to cultivar classification under nursery house and open field

Information of morphological, physiological, and pests and diseases traits between Siam or Tangerine (C. nobilis L.) and Keprok or Mandarin (C. sinensis) seedlings group under nursery and open filed condition in Indonesia has limited. The contribution of morphological and physiological characters to cultivar classification of Siam and Mandarin group has also not been yet documented. The aims of this research were to evaluate the morphological, physiological, pests and diseases responses of citrus seedling cultivars, and their contribution to cultivar classification. This research was conducted at Tlekung Experimental Garden, Citrus and Subtropical Fruits Research Institute, Batu, East Java, Indonesia from February to December 2020. One-year-old budded seedlings were planted in plastic bags (size 15x30 cm) and put in both a nursery house and open field. The plastic bags were filled with mixed media (rice hull, soil, and compost) with the ratio of 1:1:1. The experimental design was a Two Stage Nested Design consisted of two factors, these were factor A: locations (nursery house and open field) and factor B as a nested-on factor A: cultivars (Siam cv. Pontianak, Siam cv. Banjar, Siam cv. Madu, Keprok cv. Kacang, Keprok cv. Terigas, Keprok cv. Madura and Keprok cv. Gayo). The results showed that the highest flush growth percentage was showed by Keprok cv. Madura grown under open field condition, while the biggest rootstock diameter was obtained from Siam cv. Madu grown in nursery house. Siam cv. Madu grown in open field also produced the highest root dry weight and stomata density. In terms of pests and diseases, aphids (Aphis gossypii) and leaf miner (Phyllocnistis citrella) have only been affected by locations, while for diseases was not found in this study. Contribution of morphological and physiological traits to citrus cultivars classification were about 64.70%. The average percentage of change in growth and develop capacity of Keprok group from open field to the nursery house increased by 2.35%, whereas for Siam one tended to decrease by 8.96%. In general, responses of morphological and/or physiological traits between Siam and mandarin group two locations were varied. Morphological and physiological traits may also useful for supporting genetically evaluation in improving citrus breeding programs.

Tea cultivar classification and biochemical parameter estimation from hyperspectral imagery obtained by UAV

It is generally feasible to classify different species of vegetation based on remotely sensed images, but identification of different sub-species or even cultivars is uncommon. Tea trees (Camellia sinensisL.) have been proven to show great differences in taste and quality between cultivars. We hypothesize that hyperspectral remote sensing would make it possibly to classify cultivars of plants and even to estimate their taste-related biochemical components. In this study, hyperspectral data of the canopies of tea trees were collected by hyperspectral camera mounted on an unmanned aerial vehicle (UAV). Tea cultivars were classified according to the spectral characteristics of the tea canopies. Furthermore, two major components influencing the taste of tea, tea polyphenols (TP) and amino acids (AA), were predicted. The results showed that the overall accuracy of tea cultivar classification achieved by support vector machine is higher than 95% with proper spectral pre-processing method. The best results to predict the TP and AA were achieved by partial least squares regression with standard normal variant normalized spectra, and the ratio of TP to AA—which is one proven index for tea taste—achieved the highest accuracy (RCV= 0.66, RMSECV= 13.27) followed by AA (RCV= 0.62, RMSECV= 1.16) and TP (RCV= 0.58, RMSECV= 10.01). The results indicated that classification of tea cultivars using the hyperspectral remote sensing from UAV was successful, and there is a potential to map the taste-related chemical components in tea plantations from UAV platform; however, further exploration is needed to increase the accuracy.