Jove
Visualize
Contact Us

Related Experiment Videos

Content-based image retrieval: a new promising technique in powder technology.

N Laitinen1, O Antikainen, J P Mannermaa

  • 1Pharmaceutical Technology Division, University of Helsinki, Finland. niklas.laitinen@helsinki.fi

Pharmaceutical Development and Technology
|May 16, 2000
PubMed
Summary

Content-based image retrieval (CBIR) shows promise for analyzing pharmaceutical powders by correlating image similarity with particle size and appearance. However, current texture features require further development for comprehensive powder analysis.

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

Spectroscopic insight for tablet compression.

European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V·2014
Same author

Real-time image-based investigation of spheronization and drying phenomena using different pellet formulations.

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2011
Same author

New insights into segregation during tabletting.

International journal of pharmaceutics·2010
Same author

Microscale granulation in a fluid bed powder processor using electrostatic atomisation.

European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V·2008
Same author

Better understanding of dissolution behaviour of amorphous drugs by in situ solid-state analysis using Raman spectroscopy.

European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V·2008
Same author

Stable aqueous film coating dispersion of zein.

Journal of colloid and interface science·2008
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

Area of Science:

  • Pharmaceutical technology
  • Materials science
  • Image analysis

Background:

  • Pharmaceutical powder characterization is crucial for product quality and performance.
  • Traditional methods may not fully leverage the information contained in powder images.
  • Content-based image retrieval (CBIR) offers a novel approach to image analysis.

Purpose of the Study:

  • To introduce and evaluate a new CBIR technique for analyzing pharmaceutical powder systems.
  • To assess the correlation between image similarity and physical characteristics like particle size and appearance.
  • To determine the adequacy of texture features for powder analysis using CBIR.

Main Methods:

  • Utilized the QBIC (Query-by-Image-Content) system for CBIR.
  • Analyzed texture features of microcrystalline cellulose powder images.

Related Experiment Videos

  • Compared image similarity rankings with particle size and visual appearance of different powder mixtures.
  • Used pure Avicel PH 101 and Avicel PH 200 images as query images.

    • Main Results:

    • Image similarity values closely matched the appearance and particle size of powder mixtures.
    • Queries with pure Avicel PH 101 predominantly matched images of smaller particles.
    • Queries with pure Avicel PH 200 predominantly matched images of larger particles.
    • The CBIR system successfully extracted relevant content information from powder images.

    Conclusions:

    • CBIR is a promising approach for utilizing image data in pharmaceutical powder technology.
    • Current texture features are not entirely sufficient for detailed powder analysis.
    • Further development of feature extraction algorithms is necessary for an effective CBIR tool in powder technology.