International Journal of Academic Information Systems Research (IJAISR)
  Year: 2021 | Volume: 5 | Issue: 1 | Page No.: 94-99
Image-Based Pineapple Type Detection Using Deep Learning
Hamdan N. al Buhaisi

Abstract:
A pineapple (Ananas comosus)[1] is a tropical plant with eatable leafy foods most monetarily critical plant in the family Bromeliaceous. The pineapple is native to South America, where it has been developed for a long time. The acquaintance of the pineapple with Europe in the seventeenth century made it a critical social symbol of extravagance. Since the 1820s, pineapple has been industrially filled in nurseries and numerous tropical manors. Further, it is the third most significant tropical natural product in world creation. In the twentieth century, Hawaii was a prevailing maker of pineapples, particularly for the US; be that as it may, by 2016, Costa Rica, Brazil, and the Philippines represented almost 33% of the world's creation of pineapples. In this paper, machine learning based approach is presented for identifying type pineapple with a dataset that contains 1,312 images use 688 images for training, 295 images for validation and 329 images for testing. A deep learning technique that extensively applied to image recognition was used. use 70% from image for training and 30% from image for validation. Our trained model achieved an accuracy of 100% on a held-out test set.