Food and Beverage Calorie
Prediction with Neural Networks
Raman kumar mandall karingula Venudhar 2
Ramanjaneyulu
Dayinaboyina Associate Professor , Dept of AIML , CMR College of Engineering and Technology,
Kandlakoya
medchal Hyderabad , Telangana, India
1Assistant professor Department
of IT, CMR College of Engineering and
Technology,
Kandlakoya
medchal Hyderabad , Telangana, India
Abstract.This observe
introduces a revolutionary approach for enhancing nutritional monitoring and
selling healthful consuming behaviour via deep analyzing technology. The
primary objective is to correctly come across several meals objects and
estimate their calorie content cloth in actual-time, offering customers a smart
and customized technique to nutritional tracking performed using Python, the
gadget makes use of the cellular net architecture for food category and calorie
estimation. The proposed gadget methods meals snap shots through a web based
totally interface, figuring out gadgets hastily and supplying customers with a
accurate calorie estimate. This machine empowers people with treasured insights
into their nutritional behaviour, permitting them to song meals intake, set
dietary dreams, and make knowledgeable picks. via way of leveraging deep
studying for green and correct calorie estimation, this approach offers a
transformative solution for nutritional control. With its excessive precision,
real-time evaluation, and clever nutritional monitoring, this system has the
ability to redefine how humans monitor and optimize their dietary conduct,
fostering greater healthy lifestyles and average well-being.
Keywords:: Deep Learning, Food Calorie Estimation, Image Processing, CNN, Multi-Label Classification, Computer
Vision
1
Introduction
Rapid
advances in computer vision and deep learning have had a major impact on a wide
range of areas including healthcare and nutrition the key uses are food
detection and calorie estimation and it is estimated that a key role plays in
intelligent nutrition monitoring accurate food identification and estimation of
calorie content can help individuals make healthy nutrition decisions and
promote a healthier lifestyle increased smartphone use and growing nutritional
concerns have encouraged research into efficient and accurate calorie
estimation systems these approaches are highly susceptible to variations in
lighting conditions location and food presentation style furthermore many existing
systems related to reporting on food categories are limited and lack actual
calorie assessment skills this makes them ineffective for widespread use to
address these challenges this study uses deep learning techniques particularly
mobilenet architecture to improve the accuracy of food detection mobilenet is a
lightweight and efficient model suitable for mobile applications .
.........................
.........................
.........................
total 12 pages.
