z-logo
open-access-imgOpen Access
PREDICTIVE ANALYTICS OF BMI (BODY MASS INDEX) USING CAPTURED IMAGE ANALYSIS BY CONVOLUTIONAL NEURAL NETWORK
Author(s) -
V. Kakulapati
Publication year - 2021
Publication title -
journal of medical pharmaceutical and allied sciences
Language(s) - English
Resource type - Journals
ISSN - 2320-7418
DOI - 10.22270/jmpas.v10i6.1656
Subject(s) - convolutional neural network , body mass index , computer science , upload , artificial intelligence , credibility , image (mathematics) , artificial neural network , deep learning , machine learning , medicine , world wide web , pathology , political science , law
Body Mass Index (BMI) is a measurement of one's weight concerning his/her height. It is more an indicator of measurement of one's total body fat. BMI is very important as it is widely measuring in estimating health conditions. It is supposed that we have chances of having longer and healthier life with a healthy BMI. Identifying and classifying the BMI range with image analysis can help people predict credibility, control their BMI, and maintain a healthier life. Image analysis makes this very simple to classify the BMI range by analyzing the image using a deep learning algorithm named Convolutional Neural Networks. In this work, the user has to upload the image of a person for image processing. The training algorithm categorises it as undernourishment, healthy bmi, or high bmi. The input picture has to be a colourful image in the format .jpg, .jpeg, .png. This work can identify the BMI range successfully, and we got an accuracy of 82% for the model. The input picture is categorised, and the result will fall into those three previously specified classes. This work proposes a reliable depiction that is also user-friendly, allowing anybody to effortlessly check their BMI. Therefore, based on a diagnosis of BMI through image classification, one can easily follow corresponding diet procedures and maintain a healthy BMI, making it easy and supportive for the nutritionists to analyze and diagnose a patient's health status.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here