A Deep Learning Approach Towards Indian Culinary Classification

Abstract

With the rapid development of deep learning, food 
image classification has gained significant attention due 
to its potential applications in dietary monitoring, 
mobile health, and food tourism. This paper presents an 
efficient approach for classifying Indian food items 
using the Mobile Net architecture, known for its speed 
and performance on resource-constrained devices. The 
proposed model was trained on a dataset comprising ten 
Indian food categories and achieved an impressive 
classification accuracy of 98%. The results highlight 
Mobile Net’s suitability for real-time and mobile-based 
food recognition systems, especially in diverse culinary 
environments like India.