Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 6, 2026

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

Multi-Spectral Food Classification and Caloric Estimation Using Predicted Images.

¹Department of Electrical and Electronic Engineering, Konkuk University, 1 Hwayang-dong, Gwangjin-gu, Seoul 143-701, Republic of Korea.

Foods (Basel, Switzerland)

|February 24, 2024

Summary

This summary is machine-generated.

Related Concept Videos

Classification of Signals

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multispectral Food Classification and Caloric Estimation Using Convolutional Neural Networks.

Foods (Basel, Switzerland)·2023

Same journal

The Potential for Bioactive Peptide Production in a Fermented Dairy Beverage Based on Chickpea Water Extract Using Proteolytic Lactic Acid Bacteria.

Foods (Basel, Switzerland)·2026

Same journal

Influence of Protein Concentration on Heat-Induced Fouling of Oat Drink.

Foods (Basel, Switzerland)·2026

Same journal

Microalgae as Future Foods: Unlocking Their Potential and Overcoming Barriers to Market Adoption and Commercialization.

Foods (Basel, Switzerland)·2026

Same journal

Effect of High-Intensity Ultrasound and Calcium Chelation on Functional Properties of Casein Micelles.

Foods (Basel, Switzerland)·2026

Same journal

GC-MS and GC-IMS Based Metabolomics Combined with Cellular Assays to Characterize Volatile Compounds and Pharmacological Activity of <i>Lysimachia foenum-graecum</i> Hance from Different Origins.

Foods (Basel, Switzerland)·2026

Same journal

Research on the Potential Mechanism of Guanine Nucleotides Enhancing the Tolerance of <i>Lactiplantibacillus plantarum</i> Y12.

Foods (Basel, Switzerland)·2026

See all related articles

This study introduces a new method for food recognition using only standard red-green-blue (RGB) images. It accurately classifies foods and estimates calories, mimicking multi-wavelength imaging with less complexity.

Area of Science:

Nutrition science
Computer vision
Image processing

Background:

Continuous food recognition with minimal user input is crucial in nutrition science.
Multi-wavelength imaging (UV, NIR) enhances food classification and caloric estimation accuracy.
Multi-wavelength imaging presents practical challenges due to increased analysis time and light sources.

Purpose of the Study:

To develop a method for accurate food recognition and caloric estimation using only standard red-green-blue (RGB) images.
To approximate the performance of multi-wavelength imaging techniques without requiring multiple light sources.
To reduce the complexity and analysis time associated with advanced food recognition methods.

Main Methods:

Proposed a novel method utilizing deep neural networks (DNN) to predict multi-wavelength images (including UV and NIR) from standard RGB images.

Keywords:

caloric estimation convolutional neural network food recognition image conversion multispectral imaging

More Related Videos

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: May 6, 2026

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Employed DNNs to generate predicted spectral images, bypassing the need for actual multi-wavelength data acquisition.

Validated the method's effectiveness through feasibility tests on 101 diverse food items.

Main Results:

Achieved high food recognition rates: 99.45% with actual multi-wavelength images and 98.24% with predicted images.
Demonstrated significantly improved recognition compared to using only RGB images (86.3% rate).
Obtained comparable caloric estimation accuracy, with minimum Mean Absolute Percentage Errors (MAPE) of 11.67% (actual) and 12.13% (predicted).

Conclusions:

The proposed method effectively uses standard RGB images to achieve performance similar to complex multi-wavelength imaging for food recognition and caloric estimation.
This approach offers a practical and efficient alternative to multi-wavelength techniques, reducing implementation challenges.
The findings support the potential of RGB-based deep learning models for advanced nutritional analysis.