Smart Computing- Book ISBN- 978-81-953658-1-4

Authors:-Urvashi Rakholiya, Chirag patel, Ankita Gandhi, Hetal Bhaidasna

Abstract :-Picture recovery and characterisation in the food field have increasingly concerned examination points in interactive media investigation and applications. In ongoing years, with the quick advancement of the Internet business and sight and sound innovation, picture order and recovery innovation has become an exploration hotspot at home and abroad. Based on this, this paper proposes research on food image classification and image retrieval methods based on visual features, machine learning, CNN, R-CNN network and uses an adaptive learning rate is presented for training neural networks. Most probably conventional updating methods in which the learning rate gradually decreases and increases during the training period. Experiments with well-known datasets to train a multilayer perceptron show that the proposed method effectively obtains better test accuracy under certain conditions.

Keywords:- Deep Learning, CNN; Food Dataset; Food Recognition; Machine Learning; CNN Classifications.