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: Jun 20, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Signature detection and matching for document image retrieval.

Guangyu Zhu1, Yefeng Zheng, David Doermann

  • 1Language and Media Processing Laboratory, Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742, USA. zhugy@umiacs.umd.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 19, 2009
PubMed
Summary

This study introduces a new method for detecting and segmenting signatures in documents, improving document image retrieval. The approach uses multiscale analysis and novel shape matching for accurate signature identification.

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

Towards the construction of a virtual yeast.

Nature·2026
Same author

Electronics with switchable flexibility for 3D conforming neural interfaces.

Science advances·2026
Same author

IQE-CLIP: Instance-Aware Query Embedding for Zero-/Few-Shot Anomaly Detection in Medical Domain.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Leveraging Text-Modulated Semantic Guidance for Low-Light Endoscopic Image Enhancement.

IEEE transactions on medical imaging·2026
Same author

Towards generalizable AI in medicine via Generalist-Specialist Collaboration.

Nature biomedical engineering·2026
Same author

FedSemiDG: Domain generalized federated semi-supervised medical image segmentation.

Medical image analysis·2026

Area of Science:

  • Computer Vision
  • Document Image Analysis
  • Pattern Recognition

Background:

  • Signatures are crucial for identification and document authentication.
  • Detecting and segmenting signatures from complex backgrounds remains a challenge in document analysis.
  • Effective signature retrieval is vital for document image processing.

Purpose of the Study:

  • To develop a novel multiscale approach for jointly detecting and segmenting signatures.
  • To propose new methods for unconstrained, nonrigid signature shape matching for retrieval.
  • To enhance document image retrieval and offline signature verification systems.

Main Methods:

  • A multiscale detection framework capturing structural saliency and dynamic curvature of 2D contours.
  • Novel shape dissimilarity measures based on anisotropic scaling and registration residual error.

More Related Videos

Biomolecular Detection employing the Interferometric Reflectance Imaging Sensor (IRIS)
11:04

Biomolecular Detection employing the Interferometric Reflectance Imaging Sensor (IRIS)

Published on: May 3, 2011

Related Experiment Videos

Last Updated: Jun 20, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Biomolecular Detection employing the Interferometric Reflectance Imaging Sensor (IRIS)
11:04

Biomolecular Detection employing the Interferometric Reflectance Imaging Sensor (IRIS)

Published on: May 3, 2011

  • A supervised learning framework using Linear Discriminant Analysis (LDA) to combine shape information.

    • Main Results:

    • The proposed detection framework is general and computationally tractable.
    • The shape matching techniques achieve translation, scale, and rotation invariance.
    • Extensive experiments on large English and Arabic document collections demonstrate excellent performance.

    Conclusions:

    • The novel multiscale approach effectively detects and segments signatures.
    • The proposed shape matching methods significantly improve signature retrieval accuracy.
    • The techniques are validated for both document retrieval and offline signature verification.