research-article

MSER and SIMSER Regions: A Link Between Local Features and Image Segmentation

Author:

Andrzej ŚluzekAuthors Info & Claims

CGDIP '17: Proceedings of the 2017 International Conference on Computer Graphics and Digital Image Processing

Article No.: 15, Pages 1 - 5

https://doi.org/10.1145/3110224.3110227

Published: 02 July 2017 Publication History

Get Access

Abstract

In this paper, the concept of using salient regions (MSER and SIMSER features) for image segmentation is revised and evaluated. Although we focus on the foreground-background segmentation (which plays an important role of many machine vision problems) the presented results and conclusions are also applicable to more general tasks of segmentation. It is shown that standard MSER features do not provide satisfactory performances in typical segmentation problems, while SIMSER features (which are fully scale-invariant modifications of MSERs) are a more promising tool, with only marginally higher computational costs than MSERs. The presented conclusions are illustrated by exemplary results on a challenging benchmark dataset.

References

[1]

Zhang, H., Fritts, J.E., and Goldman, S.A.2008. Image segmentation evaluation: A survey of unsupervised methods. Comp. Vision & Image Understanding110 (May2008), 260--280.

Digital Library

Google Scholar

[2]

Rother, C., Kolmogorov, V., and Blake, A. 2004. GrabCut: interactive foreground extraction using iterated graph cuts. In: ACM Transaction on Graphics 23, 3 (Aug. 2004), 309--314.

Digital Library

Google Scholar

[3]

Bruce, N., and Tsotsos, J.2006.Saliency based on information maximization. In Advances in Neural Information Processing Systems 18, 155--162. MIT Press, 2006.

Digital Library

Google Scholar

[4]

Tuytelaars, T., and Mikolajczyk, K. 2007. Local invariant feature detectors: A survey. In Foundations and Trends® in Computer Graphics and Vision 3,2 (2007), 177--280.

Digital Library

Google Scholar

[5]

Matas, J., Chum, O., Urban, M., and Pajdla, T. 2004. Robust wide baseline stereo from maximally stable extremal regions. Image & Vision Computing 22, 10 (Sept. 2004), 761--767.

Crossref

Google Scholar

[6]

Nister, D., Stewenius, H. 2008. Linear time maximally stable extremal regions. In: Proc. 10th European Conf. ECCV 2008 (LNCS 5303), 183--196.

Digital Library

Google Scholar

[7]

Sluzek, A. 2016.Improving performances of MSER features in matching and retrieval tasks. In: Proc.ECCV2016Workshops(LNCS 9915), Oct. 2016, 759--770.

Google Scholar

[8]

Salahat, E., Saleh, H., Sluzek, A., Al-Qutayri, M., Mohammed, B., and Ismail, M. 2015. A maximally stable extremal regions system-on-chip for real-time visual surveillance, In Proc.41stAnnual Conf. IEEE Industrial Electronics Society (Nov. 2015), 2812-2915.

Google Scholar

[9]

Peng, R., and Varshney, P.K. 2015. On performance limits of image segmentation algorithms. Comp. Vision & Image Understanding 132 (March 2015), 24--38.

Digital Library

Google Scholar

[10]

Donoser, M., Bischof, H., and Wiltsche, M. 2006. Color blob segmentation by MSER analysis. In: Proc. IEEE Int. Conf. on Image Proc. ICIP 2006 (Oct. 2006).

Google Scholar

[11]

Gui, Y., Zhang, X., and Shang, Y. 2012. SAR image segmentation using MSER and improved spectral clustering. EURASIP Journal of Adv. Signal Processing 83 (Dec. 2012).

Google Scholar

[12]

Oh, I.S., Lee, J., Majumder, A. 2013. Multi-scale image segmentation using MSER. In: Proc. 15th Int. Conf. CAIP 2013, Vol. II., (2013) 201--208.

Crossref

Google Scholar

[13]

Li, H., Cai, J., Nguyen, T.N.A., and Zheng, J. 2013. A benchmark for semantic image segmentation. In: Proc IEEE Int. Conf. Multimedia and Expo ICME (July 2013)

Google Scholar

Cited By

View all

Lahouli IChtourou ZAyed MHaelterman RDe Cubber GAttia R(2019)Pedestrian Detection and Trajectory Estimation in the Compressed Domain Using Thermal ImagesComputer Vision, Imaging and Computer Graphics Theory and Applications10.1007/978-3-030-26756-8_10(212-227)Online publication date: 24-Jul-2019
https://doi.org/10.1007/978-3-030-26756-8_10
Lahouli IHaelterman RChtourou ZDe Cubber GAttia R(2019)Pedestrian Tracking in the Compressed Domain Using Thermal ImagesCommunications, Signal Processing, and Systems10.1007/978-3-030-19816-9_3(35-44)Online publication date: 5-May-2019
https://doi.org/10.1007/978-3-030-19816-9_3
Śluzek A(2018)Scale-Insensitive MSER Features: A Promising Tool for Meaningful Segmentation of ImagesBridging the Semantic Gap in Image and Video Analysis10.1007/978-3-319-73891-8_3(31-50)Online publication date: 21-Feb-2018
https://doi.org/10.1007/978-3-319-73891-8_3

Index Terms

MSER and SIMSER Regions: A Link Between Local Features and Image Segmentation
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
        Image segmentation
        Interest point and salient region detections
      2. Computer vision tasks
2. Information systems
  1. Information retrieval
    1. Specialized information retrieval
      1. Multimedia and multimodal retrieval
        Image search

Recommendations

Multi-distinctive MSER Features and Their Descriptors: A Low-Complexity Tool for Image Matching
ACIVS 2015: Proceedings of the 16th International Conference on Advanced Concepts for Intelligent Vision Systems - Volume 9386

The paper proposes multi-distinctive MSER featuresmd-MSER which are MSER keypoints combined with a number of encompassed keypoints of another type, which should also be affine-invariants e.g. Harris-Affine keypoints to maintain the invariance of the ...
A Novel Wide-Baseline Stereo Matching Algorithm Combining MSER and DAISY
CSAE '18: Proceedings of the 2nd International Conference on Computer Science and Application Engineering

Image1 matching is a fundamental problem in Computer Vision. In the context of feature-based matching, SIFT (Scale-Invariant Feature Transform) and its variants have long excelled in a wide array of applications. However, for wide-baseline images, it is ...
An evaluation of local interest regions for non-rigid object class recognition

Highlights EdgeLap, SURF, HarAff, HesAff, kAS, FAST, IBR, PCBR, HarLap, HesLap, Salient, MSER, and DoG are evaluated. EdgeLap interest region detector reaches to the highest success-rate. A new discriminancy measure based on random region success-rate ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

CGDIP '17: Proceedings of the 2017 International Conference on Computer Graphics and Digital Image Processing

July 2017

130 pages

ISBN:9781450352369

DOI:10.1145/3110224

Editor:
Ahmad H. Nasri

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Auckland University of Technology

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 02 July 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

CGDIP '17

CGDIP '17: 2017 International Conference on Computer Graphics and Digital Image Processing

July 2 - 4, 2017

Prague, Czech Republic

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
90
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 25 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Lahouli IChtourou ZAyed MHaelterman RDe Cubber GAttia R(2019)Pedestrian Detection and Trajectory Estimation in the Compressed Domain Using Thermal ImagesComputer Vision, Imaging and Computer Graphics Theory and Applications10.1007/978-3-030-26756-8_10(212-227)Online publication date: 24-Jul-2019
https://doi.org/10.1007/978-3-030-26756-8_10
Lahouli IHaelterman RChtourou ZDe Cubber GAttia R(2019)Pedestrian Tracking in the Compressed Domain Using Thermal ImagesCommunications, Signal Processing, and Systems10.1007/978-3-030-19816-9_3(35-44)Online publication date: 5-May-2019
https://doi.org/10.1007/978-3-030-19816-9_3
Śluzek A(2018)Scale-Insensitive MSER Features: A Promising Tool for Meaningful Segmentation of ImagesBridging the Semantic Gap in Image and Video Analysis10.1007/978-3-319-73891-8_3(31-50)Online publication date: 21-Feb-2018
https://doi.org/10.1007/978-3-319-73891-8_3

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Abstract

References

Cited By

Index Terms

Recommendations

Multi-distinctive MSER Features and Their Descriptors: A Low-Complexity Tool for Image Matching

A Novel Wide-Baseline Stereo Matching Algorithm Combining MSER and DAISY

An evaluation of local interest regions for non-rigid object class recognition

Comments

Information

Published In

In-Cooperation

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Login options

Full Access

View options

PDF

eReader

Share

Share this Publication link

Share on social media

Affiliations