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

Image shadow removal using pulse coupled neural network.

Xiaodong Gu1, Daoheng Yu, Liming Zhang

  • 1Department of Electronic Engineering, Fudan University, Shanghai 200433, China. guxiaodong@263.net

IEEE Transactions on Neural Networks
|June 9, 2005
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

Inhibitory Effects of Genistein on Vascular Smooth Muscle Cell Proliferation Induced by Ox-LDL: Role of BKCa Channels.

Analytical cellular pathology (Amsterdam)·2021
Same author

Spatial distribution and eco-environmental risk assessment of heavy metals in surface sediments from a crater lake (Bosomtwe/Bosumtwi).

Environmental science and pollution research international·2021
Same author

Corrigendum to "Enhancing bio-catalytic activity and stability of lipase nanogel by functional ionic liquids modification" [Colloids Surf. B: Biointerfaces 195 (2020) 111275].

Colloids and surfaces. B, Biointerfaces·2020
Same author

Could computed tomography be used as a surrogate of endoscopic ultrasonography in the screening and surveillance of small gastric Gastrointestinal stromal tumors?

European journal of radiology·2020
Same author

Improvement of Postharvest Anthracnose Resistance in Mango Fruit by Nitric Oxide and the Possible Mechanisms Involved.

Journal of agricultural and food chemistry·2020
Same author

Affine Transformation-Enhanced Multifactorial Optimization for Heterogeneous Problems.

IEEE transactions on cybernetics·2020

This study presents a novel image shadow removal technique using pulse coupled neural networks (PCNNs). The method effectively removes shadows from images, preserving original image quality and object shapes.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Image Processing

Background:

  • Image shadow removal is a challenging problem in computer vision.
  • Existing methods may struggle with preserving image details or handling varying shadow conditions.

Purpose of the Study:

  • To introduce an efficient image shadow removal approach using pulse coupled neural networks (PCNNs).
  • To propose two criteria for optimizing PCNN parameters for effective shadow removal.

Main Methods:

  • Utilizing pulse coupled neural networks (PCNNs), inspired by biological visual cortex phenomena.
  • Developing two specific criteria to determine the optimal linking strength (beta) parameter for PCNNs.
  • Applying the method to both grayscale and color images, including channel division for color images.

Related Experiment Videos

Main Results:

  • PCNN-based shadow removal successfully eliminates shadows when proposed criteria are met.
  • Shadow-removed images closely resemble original non-shadowed images.
  • The method demonstrates robustness to variations in shadow intensity and location.
  • Object shapes are preserved, even when only one criterion is satisfied for natural grayscale images.

Conclusions:

  • The proposed PCNN-based approach offers an effective solution for image shadow removal.
  • The two criteria provide a reliable method for parameter selection in PCNNs for shadow removal.
  • This technique is applicable to various image types and shadow conditions, excluding those with significant random noise.