Grape Type Classification Using Deep Learning

Download Edit this record How to cite View on PhilPapers
Abstract
Abstract: A grape is a fruit, botanically a berry, of the deciduous woody vines of the flowering plant genus Vitis. it can be eaten fresh or they can be used for making jam, grape juice, jelly, grape seed extract, raisins, and grape seed oil. Grapes are a nonclimacteric type of fruit, generally occurring in clusters. Grapes are a type of fruit that grow in clusters of 15 to 300, and can be crimson, black, dark blue, yellow, green, orange, and pink. "White" grapes are actually green in color, and are evolutionarily derived from the purple grape. Mutations in two regulatory genes of white grapes turn off production of anthocyanins, which are responsible for the color of purple grapes. Grapes are typically an ellipsoid shape resembling a prolate spheroid. In this paper, machine learning based approach is presented for identifying type Grapes with a dataset that contains 4,565 images use 2,393 images for training, 1,026 images for validation and 1,146 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, demonstrating the feasibility of this approach.
Categories
(categorize this paper)
PhilPapers/Archive ID
ELMGTC-2
Upload history
Archival date: 2020-01-01
View other versions
Added to PP index
2020-01-01

Total views
70 ( #49,606 of 2,444,557 )

Recent downloads (6 months)
16 ( #39,094 of 2,444,557 )

How can I increase my downloads?

Downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.