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 Videos

A flower image retrieval method based on ROI feature.

An-Xiang Hong1, Gang Chen, Jun-Li Li

  • 1Department of Applied Mathematics, Zhejiang University, Hangzhou 310027, China. Hax@nbit.gov.cn

Journal of Zhejiang University. Science
|October 21, 2004
PubMed
Summary
This summary is machine-generated.

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

MiR-27a promotes hepatocellular carcinoma cell proliferation through suppression of its target gene peroxisome proliferator-activated receptor γ.

Chinese medical journal·2015
Same author

Expression and Characterization of a Recombinant Laccase with Alkalistable and Thermostable Properties from Streptomyces griseorubens JSD-1.

Applied biochemistry and biotechnology·2015
Same author

Herb-Partitioned Moxibustion and the miRNAs Related to Crohn's Disease: A Study Based on Rat Models.

Evidence-based complementary and alternative medicine : eCAM·2015
Same author

Bioactive carbazole alkaloids from the stems of Clausena lansium.

Fitoterapia·2015
Same author

Clauemarazoles A-G, seven carbazole alkaloids from the stems of Clausena emarginata.

Fitoterapia·2015
Same author

Scalable and DiI-compatible optical clearance of the mammalian brain.

Frontiers in neuroanatomy·2015
Same journal

Enhancing the quality metric of protein microarray image.

Journal of Zhejiang University. Science·2004
Same journal

Mathematical modeling of salt-gradient ion-exchange simulated moving bed chromatography for protein separations.

Journal of Zhejiang University. Science·2004
Same journal

Characterization of cellulose acetate micropore membrane immobilized acylase I.

Journal of Zhejiang University. Science·2004
Same journal

Research on the rheological properties of pesticide suspension concentrate.

Journal of Zhejiang University. Science·2004
Same journal

Ant colony system algorithm for the optimization of beer fermentation control.

Journal of Zhejiang University. Science·2004
Same journal

Scale-up of rifamycin B fermentation with Amycolatoposis mediterranei.

Journal of Zhejiang University. Science·2004
See all related articles

This study introduces an efficient method for extracting flower regions using color clustering and domain knowledge. The approach improves flower image retrieval accuracy by combining color and shape features.

Area of Science:

  • Computer Vision
  • Botany
  • Image Processing

Background:

  • Accurate plant species recognition relies heavily on effective flower image retrieval.
  • Existing methods for flower image retrieval have limitations in accuracy and efficiency.

Purpose of the Study:

  • To develop an efficient segmentation method for extracting flower regions from images.
  • To enhance flower image retrieval accuracy using combined color and shape features.

Main Methods:

  • A novel segmentation technique utilizing color clustering and domain knowledge for precise flower region extraction.
  • Feature extraction employing color histograms for color characteristics and Centroid-Contour Distance (CCD) and Angle Code Histogram (ACH) for shape analysis.
  • Region-of-Interest (ROI) based retrieval integrating both color and shape features.

Related Experiment Videos

Main Results:

  • The proposed method accurately extracts flower regions, outperforming previous techniques.
  • Experimental results on an 885-image database demonstrate superior retrieval performance compared to global color histogram and domain knowledge-based methods.
  • The combined color and shape feature approach significantly enhances retrieval accuracy.

Conclusions:

  • The developed segmentation method effectively isolates flower regions for improved image analysis.
  • The ROI-based retrieval strategy, incorporating both color and shape features, offers a more robust and accurate solution for flower image retrieval and plant recognition.