New Frontiers in Communication and Intelligent Systems
A Novel Method to Detect Freshness and Edibility of Betel Leaves Using Convolutional Neural Networks
Authors: Vishwa Hatwalne, Ankit Gundewar, Siddhant Shenoy, Fedrick Francisco Pereira Neto and Malathi G
Publishing Date: 06-05-2022
ISBN: 978-81-95502-00-4
Abstract
Analyzing the edibility of consumables by the human body is very crucial to identify the nutritional values absorbed. Not consuming fresh or edible food can lead to various problems like food poisoning and low immunity. Identifying such problems at the stage of consumption can help in preventing several food borne diseases and improve health. Technology can be heavily used to determine the freshness and edibility of food items. During these pandemic times, people have been looking for food items which enhance immunity. One such item is Betel Leaf. In this research we have used techniques like Image Segmentation and Convolutional Neural Networks (CNN) to design a model which can accurately determine the freshness of the betel leaf. Image segmentation is used to extract the leaf from the image and Convolutional Neural Networks is used to extract features from the extracted leaf image. These features are then learnt by the model which classifies the leaf as the ones which are rotten and are not fresh, as ‘stale’ and the ones which are lush green and visibly fresh as ‘fresh’. Therefore, this research would be of great use to automate the process of analyzing the freshness and edibility of the betel leaf.
Keywords
Image Processing, Deep Learning, Computer Vision, Convolutional Neural Networks, Betel Leaf, Disease Identification.
Cite as
Vishwa Hatwalne, Ankit Gundewar, Siddhant Shenoy, Fedrick Francisco Pereira Neto and Malathi G, "A Novel Method to Detect Freshness and Edibility of Betel Leaves Using Convolutional Neural Networks", In: Rahul Srivastava and Aditya Kr. Singh Pundir (eds), New Frontiers in Communication and Intelligent Systems, SCRS, India, 2022, pp. 517-523. https://doi.org/10.52458/978-81-95502-00-4-53