Image Based Estimation of Food Colories Based on Machine Learning

For the last few decades, it has been the popular trend in India that people are putting more attention on improving their healthiness and regulating calorie intake for every meal, so that we build a model for calorie estimation of various food. Dieticians and healthcare conventions are concerned with the consumption of accurate quantity and right kind of food. There is no doubt that exercising also plays a vital role but what we are feeding our body plays a major role in obesity and many problems related to health like diabetes, stroke, and many cardio vascular diseases. Also, due to advancement in technology, today’s generation can order food just with a click on their mobile devices. Thus, acceleration in obesity is evident. For the people who are concerned with this problem, keeping the records of the consumption of nutrients manually is difficult. To combat this, a variety of health applications and Calorie measurement tools have emerged to reverse or shrink the effect of all the health-related troubles. Some of the applications also utilize state-of-the-art Artificial Intelligence algorithms. In this project, a machine learning based model which estimates the calories in various food elements with the help of Ensemble Bagginig Supervised Classification Machine Learning algorithms with feature extraction using Resnet-101 pre-trained Deep Convolutional Neural Network Model. The proposed model is developed and evaluated in MATLAB R2018b, it is also found that proposed system has better efficiency than existing method.