Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 23, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Detection of fraud in ginger powder using an automatic sorting system based on image processing technique and deep

Ahmad Jahanbakhshi1, Yousef Abbaspour-Gilandeh1, Kobra Heidarbeigi2

  • 1Department of Biosystems Engineering, University of Mohaghegh Ardabili, Ardabil, Iran.

Computers in Biology and Medicine
|August 24, 2021
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Harnessing social media data to track species range shifts.

Conservation biology : the journal of the Society for Conservation Biology·2026
Same author

Nondestructive Detection of Polyphenol Oxidase Activity in Various Plum Cultivars Using Machine Learning and Vis/NIR Spectroscopy.

Foods (Basel, Switzerland)·2025
Same author

Application of hyperspectral imaging to the automatic assessment of polyphenol oxidase and peroxidase enzymatic activity levels in bell pepper cultivars.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2025
Same author

Application of ultrasound treatment in cantaloupe infrared drying process: Effects on moisture migration and microstructure.

Journal of food science·2025
Same author

Optimization of environmental and energy performance of egg production using data envelopment analysis (DEA) and life cycle assessment (LCA).

The Science of the total environment·2025
Same author

Evaluation of emissions and performance of a diesel engine running on graphene nanopowder and diesel-biodiesel-ethanol blends.

Environmental science and pollution research international·2024

This study developed an improved convolutional neural network (CNN) using gated pooling and batch normalization to detect adulterated ginger powder. The method achieved 99.70% accuracy in identifying fraud, offering a reliable solution for spice quality control.

Area of Science:

  • Food Science
  • Computer Vision
  • Artificial Intelligence

Background:

  • Ginger is a valuable spice frequently adulterated with cheaper ingredients like chickpea powder for economic gain.
  • Traditional methods for detecting adulteration are often time-consuming and lack accuracy.
  • There is a growing demand for non-destructive, automated methods for food quality assessment.

Purpose of the Study:

  • To develop and evaluate an improved convolutional neural network (CNN) for detecting adulteration in ginger powder.
  • To enhance CNN performance through a novel gated pooling function combined with average and max pooling.
  • To assess the effectiveness of Batch Normalization (BN) in improving classification accuracy for ginger powder fraud detection.

Main Methods:

  • A dataset of 3360 ginger powder images across 7 categories (pure and 50% adulterated with chickpea powder) was created.
Keywords:
Convolutional neural networksDeep learningFood fraudGinger powderMachine vision

More Related Videos

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

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

Published on: February 14, 2018

11.5K
Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System
08:02

Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System

Published on: October 4, 2024

2.7K

Related Experiment Videos

Last Updated: Oct 23, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

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

Published on: February 14, 2018

11.5K
Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System
08:02

Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System

Published on: October 4, 2024

2.7K
  • A modified CNN architecture incorporating a gated pooling function and Batch Normalization was proposed.
  • The proposed CNN model was compared against traditional machine learning algorithms including MLP, Fuzzy, SVM, GBT, and EDT.

    • Main Results:

    • The enhanced CNN model, utilizing gated pooling and BN, achieved a classification accuracy of 99.70% for detecting adulterated ginger powder.
    • The proposed gated pooling method demonstrated superior performance compared to baseline pooling techniques.
    • The CNN approach significantly outperformed other tested machine learning algorithms in accuracy.

    Conclusions:

    • The developed CNN model with gated pooling and BN is highly effective for accurate and non-destructive detection of ginger powder adulteration.
    • This image processing technique can enhance marketability, prevent economic fraud, and support traditional quality control methods.
    • The study highlights the potential of advanced AI in ensuring the integrity of food and spice products.