Application of Artificial Intelligence for on-farm recognition of matured pineapple for harvesting

Abstract

Agriculture is seeing rapid adoption of Artificial Intelligence (AI) in terms of agricultural products and in-field farming techniques. AI in agriculture is emerging in three major categories i.e. agricultural robotics, soil and crop monitoring, and predictive analytics. This article presents a comprehensive application of artificial intelligence to recognize the matured pineapple for harvesting in the field. Pineapple fruit has a crucial maturity period.The skin of the fruit changes from pale green to a golden or yellowish color at maturity. However, this maturity level often makes farmers confused and results in wrong decision, and many resulting loss in yield. Therefore, an Artificial Intelligence (AI) based automatic system has been designed and developed for identifying the most matured pineapple. This technique involves computer vision and machine learning techniques based algorithm using Haar-like features. Python language has been used to evaluate the features of a matured pineapple. The developed detection system works in two steps namely, (1) by extracting the Haar-like features of grey scale image and classifying with the AdaBoost classifier, to identify the pineapple; (2) the HSV colour space limits setting to identify the matured pineapple colouras calculated by the algorithm. The developed system was field tested and found to succeed in the identification of 93% the correct fruits.