Evaluation of Image Processing Technique on Quality Properties of Chickpea Seeds (Cicer arietinum L.) Using Machine Learning Algorithms

Chickpea is an important edible legume consumed worldwide because of rich nutrient composition. The physical parameters of chickpea are crucial attributes for design of processing and classification systems. In this study, effects of seven different irrigation treatments (I1-rainfed, I2-pre-flowering single irrigation, I3-beginning of flowering single irrigation, I4-50% pod set single irrigation, I5-irrigation at 50% flowering and 50% pod fill, I6-irrigation before flowering and at 50% pod set, I7-full irrigation) on size, shape, mass, and color properties of chickpea seeds were investigated, and machine learning algorithms were used to estimate mass and color attributes of chickpea seeds. In terms of physical attributes, the best results were obtained in I1 and I5 irrigation treatments. According to the findings, among the irrigation treatments, I5 had the greatest mass, volume, geometric mean diameter, projected area with the values of 0.50 g, 394.86 cm3, 9.10 mm and 65.03 mm2, respectively. In addition, I1 had the highest shape index and elongation as 1.33 and 1.34, respectively. The results showed that multilayer perceptron (MLP) had the greatest correlation coefficients for mass (0.9997), chroma (0.9998) hue angle (0.9998) and color index (0.9992). The MLP yielded better outcomes than random forest for both mass and color estimation. Additionally, single or couple irrigation treatment at different physiological stages instead of full irrigation treatment might be sufficient to improve the physical attributes of chickpea.