• Home
  • Search
  • A Tensor Voting for Corrupted Region Inference and Text Image Segmentation
  • Cite Icon1
  • https://doi.org/10.1007/978-3-540-69423-6_73Copy DOI Icon

A Tensor Voting for Corrupted Region Inference and Text Image Segmentation

  • Jan 1, 2006
  • Jonghyun Park +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Most computer vision applications often require reliable segmentation of objects when they are mixed with corrupted text images. In the presence of noise, graffiti, streaks, shadows and cracks, this problem is particularly challenging. We propose a tensor voting framework in 3D for the analysis of candidate features. The problem has been formulated as an inference of hue and intensity layers from a noisy and possibly sparse point set in 3D. Accurate region layers are extracted based on the smoothness of color features by generating candidate features with outlier rejection and text segmentation. The proposed method is non-iterative and consistently handles both text data and background without using any prior information on the color space.

Similar Papers
  • Conference Article

Kernel ridge regression for supervised classification using Tensor Voting

  • Dec 01, 2014
  • Mandar Kulkarni +2
  • Research Article
  • Citations2

Generalized Segmentation Algorithm for Dissimilar Script Languages

  • Dec 01, 2023
  • International Journal of Scientific Research in Computer Science Engineering and Information Technology
  • Abdul Majid +3
  • Research Article
  • Citations4

Multi-Scale Skin Sample Approach for Dynamic Skin Color Detection: An Analysis

  • Oct 01, 2018
  • Advanced Science Letters
  • Mohd Zamri Osman +4
  • Research Article
  • Citations22

Transformation of a high-dimensional color space for material classification.

  • Mar 13, 2017
  • Journal of the Optical Society of America A
  • Huajian Liu +2
  • Research Article
  • Citations8

Exploring Image Representation and Color Spaces in Computer Vision: A Comprehensive Review

  • Jun 15, 2024
  • Indonesian Journal of Computer Science
  • Hewa Majeed Zangana +3
  • Research Article
  • Citations31

Layered 4D representation and voting for grouping from motion

  • Apr 01, 2003
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • M Nicolescu +1
  • Conference Article

Remote sensing image classification by mean shift and colour quantization

  • Nov 08, 2012
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Hind Taud +2
  • Research Article
  • Citations3

Methods for text segmentation from scene images

  • Jun 07, 2014
  • ELCVIA Electronic Letters on Computer Vision and Image Analysis
  • Deepak Kumar +1
  • Research Article
  • Citations17

Separation of specular and diffuse components using tensor voting in color images.

  • Nov 17, 2014
  • Applied Optics
  • Tam Nguyen +4
  • Research Article
  • Citations2

Analysis of SSIM based Quality Assessment across Color Channels of Images

  • Jul 01, 2015
  • International Journal of System Dynamics Applications
  • T Chandrakanth +1
  • Conference Article

Using Pattern Matching in the 1-D Domain of Chain Code Signals for the Compression of Binary Printed Farsi and Arabic Textual Images

  • Dec 01, 2010
  • Esmaeil Shojaei +1
  • Research Article
  • Citations8

Robust Automatic Segmentation of Inflamed Appendix from Ultrasonography with Double-Layered Outlier Rejection Fuzzy C-Means Clustering

  • Jun 06, 2022
  • Applied Sciences
  • Kwang Baek Kim +2
  • Conference Article
  • Citations12

English

  • Jan 01, 2006
  • Ekrem Misimi +3
  • Research Article
  • Citations202

An Integrated Method for Urban Main-Road Centerline Extraction From Optical Remotely Sensed Imagery

  • Jun 01, 2014
  • IEEE Transactions on Geoscience and Remote Sensing
  • Wenzhong Shi +2
  • Research Article

Integrative deep learning with prior assisted feature selection.

  • Jun 23, 2024
  • Statistics in medicine
  • Feifei Wang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.