Apple Fruit Detection and Maturity Status Classification
Deepika Srinivasan1, Mahmoud Yousef2
1Deepika Srinivasan, School of Computer Science and Mathematics, University of Central Missouri, Warrensburg, USA.
2Dr. Mahmoud Yousef, School of Computer Science and Mathematics, University of Central Missouri, Warrensburg, USA.
Manuscript received on May 25, 2020. | Revised Manuscript received on June 29, 2020. | Manuscript published on July 30, 2020. | PP: 1055-1059 | Volume-9 Issue-2, July 2020. | Retrieval Number: B4063079220/2020©BEIESP | DOI: 10.35940/ijrte.B4063.079220
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Identifying the quality of fresh produce while procuring is a major task that involves time and human effort in the retail industry. The main objective of this project is to identify and classify whether the apple fruit is fresh or rotten using Convolutional Neural Networks. The outcome of our study resulted in 97.92 percent accuracy for the 2 classes of approximately 5031 images in the classification, by identifying apples using Resnet 50 and then classifying them using the proposed model.
Keywords: Convolution Neural Network, Resnet50, Fresh Produce, Flask, and Tkinter.