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: Mar 8, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K

Scene Text Detection and Segmentation based on Cascaded Convolution Neural Networks.

Youbao Tang, Xiangqian Wu

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |January 24, 2017
    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

    EyeKey: Self-Supervised Keypoint Detection and Description Network Based on Local Feature Saliency for Retinal Image Global Registration.

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

    PalmDiff: When Palmprint Generation Meets Controllable Diffusion Model.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same author

    Capsule-Based Regression Tracking via Background Inpainting.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
    Same author

    Differential diagnosis of bone marrow failure syndromes guided by machine learning.

    Blood·2022
    Same author

    Latent Space Semantic Supervision Based on Knowledge Distillation for Cross-Modal Retrieval.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
    Same author

    A flexible three-dimensional heterophase computed tomography hepatocellular carcinoma detection algorithm for generalizable and practical screening.

    Hepatology communications·2022

    This study introduces a novel cascaded convolution neural network (CNN) method for scene text detection and segmentation. The approach enhances accuracy and efficiency in identifying and refining text regions within complex visual scenes.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Scene text detection and segmentation are critical yet challenging computer vision tasks.
    • Existing methods often struggle with accuracy and efficiency in complex visual environments.

    Purpose of the Study:

    • To propose a novel cascaded convolution neural network (CNN) based method for accurate scene text detection and segmentation.
    • To improve the efficiency of text region extraction and refinement.

    Main Methods:

    • A cascaded CNN architecture comprising a detection network (DNet), segmentation network (SNet), and classification network (CNet).
    • DNet extracts coarse candidate text regions (CTRs) using text edges and regions.
    • SNet refines CTRs for precise text segmentation, followed by CNet for classification.

    Related Experiment Videos

    Last Updated: Mar 8, 2026

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.2K

    Main Results:

    • The proposed method significantly reduces the number of extracted CTRs while preserving true text regions.
    • Achieved state-of-the-art performance on three benchmark datasets.
    • Outperformed existing scene text detection and segmentation approaches.

    Conclusions:

    • The cascaded CNN approach offers a robust and efficient solution for scene text detection and segmentation.
    • The method demonstrates superior performance compared to traditional techniques.
    • Paves the way for advancements in real-world applications requiring scene text understanding.