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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

An Adaptive Transfer Learning Framework for Multimodal Autism Spectrum Disorder Diagnosis.

Life (Basel, Switzerland)·2025
Same author

An Explainable Deep Learning Framework for Multimodal Autism Diagnosis Using XAI GAMI-Net and Hypernetworks.

Diagnostics (Basel, Switzerland)·2025
Same author

An ensemble-of-classifiers based approach for early diagnosis of Alzheimer's disease: classification using structural features of brain images.

Computational and mathematical methods in medicine·2014
See all related articles

Related Experiment Video

Updated: Apr 21, 2026

Correlative Optical Spectroscopy and Mass Spectrometry Imaging Methodology to Visualise Drug Distribution in a Soft Tissue Section
07:05

Correlative Optical Spectroscopy and Mass Spectrometry Imaging Methodology to Visualise Drug Distribution in a Soft Tissue Section

Published on: June 20, 2025

1.5K

A statistical-textural-features based approach for classification of solid drugs using surface microscopic images.

Fahima Tahir1, Muhammad Abuzar Fahiem1

  • 1Department of Computer Science, Lahore College for Women University, Jail Road, Lahore 54000, Pakistan.

Computational and Mathematical Methods in Medicine
|November 6, 2014
PubMed
Summary

This study introduces a non-destructive method using surface morphology to detect defective pharmaceutical tablets. Support Vector Machines (SVM) demonstrated superior accuracy in identifying tablet defects compared to other classifiers.

More Related Videos

Rapid Analysis and Exploration of Fluorescence Microscopy Images
11:41

Rapid Analysis and Exploration of Fluorescence Microscopy Images

Published on: March 19, 2014

11.6K
Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography
12:18

Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography

Published on: October 21, 2018

16.2K

Related Experiment Videos

Last Updated: Apr 21, 2026

Correlative Optical Spectroscopy and Mass Spectrometry Imaging Methodology to Visualise Drug Distribution in a Soft Tissue Section
07:05

Correlative Optical Spectroscopy and Mass Spectrometry Imaging Methodology to Visualise Drug Distribution in a Soft Tissue Section

Published on: June 20, 2025

1.5K
Rapid Analysis and Exploration of Fluorescence Microscopy Images
11:41

Rapid Analysis and Exploration of Fluorescence Microscopy Images

Published on: March 19, 2014

11.6K
Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography
12:18

Pore-scale Imaging and Characterization of Hydrocarbon Reservoir Rock Wettability at Subsurface Conditions Using X-ray Microtomography

Published on: October 21, 2018

16.2K

Area of Science:

  • Pharmaceutical Technology
  • Image Analysis
  • Machine Learning

Background:

  • Pharmaceutical product quality is critical for patient safety and the pharmaceutical industry.
  • Defective tablets pose significant risks to patient health.
  • Current quality control methods may not always be sufficient.

Purpose of the Study:

  • To propose and evaluate a non-destructive method for identifying defective pharmaceutical tablets.
  • To analyze the impact of environmental factors (temperature, humidity, moisture) on the detection method.
  • To compare the performance of different machine learning classifiers and feature sets.

Main Methods:

  • Surface morphology images of defective and non-defective tablets were analyzed.
  • Multiple textural features were extracted, including Gray Level Co-occurrence Matrix, Run Length Matrix, Histogram, Autoregressive Model, and HAAR wavelet.
  • Feature reduction techniques (chi-square, gain ratio, relief-F) were applied to select top features.
  • Classifiers such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes were employed.
  • Performance was evaluated using leave-one-out cross-validation and train-test models.

Main Results:

  • A comprehensive set of 281 textural features was extracted and analyzed.
  • Feature reduction identified top 15 and top 2 most informative features.
  • Support Vector Machine (SVM) generally outperformed K-Nearest Neighbors (KNN) and Naïve Bayes in accuracy.
  • The method's performance was assessed under varying temperature, humidity, and moisture conditions.

Conclusions:

  • The proposed non-destructive method based on surface morphology is effective for identifying defective pharmaceutical tablets.
  • SVM is a highly accurate classifier for this application.
  • The method shows potential for integration into pharmaceutical quality control processes.
  • Further research can explore optimization under diverse environmental conditions.