An Intelligent Bigdata Flavor Space Bizarre

Authors

  • Ms.M.SalomiSamsudeen. Dr.P. Thangaraj, Dr.A.Devipriya, Dr.M.Sivasangari, Dr.B.Gomathy

Abstract

Recently, smart applications for mobile devices such as Android phones and iPhone, have increased tremendously. Due to the advances in various technologies used in smartphones, their computational power has also increased. In the current age, people are more conscious about their food and diet. We can use this technology to help people classify different types of food and their health benefits. In this paper, an approach has been presented to classify images of food using convolutional neural networks. Unlike the traditional artificial neural networks, convolutional neural networks have the capability of estimating the score function directly from image pixels. There are multiple such layers, and the outputs are concatenated at parts to form the final tensor of outputs. We use MAX pooling to extract essential features from the images and use it to train the model. An accuracy of 86.97% for the classes of the FOOD-101 dataset is recognised using the proposed implementation.

Published

2020-11-01

Issue

Section

Articles