Development of Fruit Classification Models Using Deep Convolutional Neural Network
Author(s):
VIJAYA CHOUDHARY, PARAMITA GUHA, SUNITA MISHRA, SHIV KUMAR VERMA, B. BALAMURUGAN
Keywords:
Abstract
Classifying fruits from an image is a remarkable research area when we talk about computer vision. In this regard, this paper proposes a system where fruit detection and fruits classification are performed. In India, fruit yield is turned down because of the post conceding of many spots(disease) on the fruits by the farmers at the end. Agronomists struggle a lot for economical loss across the world. We can say that fruits diseases are the main cause of agricultural loss. To improve their productivity, it is important to know the health status of fruits to help the farmers. This motivates us to design and develop a model to help farmers detect the diseases in the early stage itself. The idea behind this work is to develop automatic models that recognize the disease's level and grade them accordingly. Convolutional neural networks opted for the classification, again retrained using the transfer learning technique. The system is developed in the Tensor flow platform. For the proposed work three to four types of fruits have been considered. The model shows 98.17% training accuracy, whereas, the deep learning-based fruits classification test model shows 99.99% accuracy.
Article Details
Unique Paper ID: 155382

Publication Volume & Issue: Volume 8, Issue 10

Page(s): 107 - 111
Article Preview & Download


Share This Article

Conference Alert

NCSST-2021

AICTE Sponsored National Conference on Smart Systems and Technologies

Last Date: 25th November 2021

SWEC- Management

LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT

Last Date: 7th November 2021

Go To Issue



Call For Paper

Volume 8 Issue 4

Last Date 25 September 2021

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies