Color Blob Segmentation by MSER Analysis

@article{Donoser2006ColorBS,
  title={Color Blob Segmentation by MSER Analysis},
  author={Michael Donoser and Horst Bischof and Mario Wiltsche},
  journal={2006 International Conference on Image Processing},
  year={2006},
  pages={757-760}
}
This paper presents an efficient color blob segmentation concept, which combines an ordering relationship based on analyzing Bhattacharyya distances with a modified version of the maximally stable extremal region (MSER) detector. After definition of the region-of-interest by a one-time user input, connected regions are detected within the input image with low computational effort. Single image and video sequence analysis results are presented, which prove the applicability of the concept… 

Figures from this paper

Multi-scale Image Segmentation Using MSER

A novel algorithm based on MSER is proposed which segments natural images without user intervention and captures multi-scale structure and hierarchical morphological operations are developed.

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

It is shown that standard MSER features do not provide satisfactory performances in typical segmentation problems, while SIMSER features are a more promising tool, with only marginally higher computational costs than MSERs.

A blur robust color image dectection method based on Maximally Stable Extremal Regions

  • Tong YuChaochao Lu
  • Computer Science
    2011 6th International Conference on Computer Sciences and Convergence Information Technology (ICCIT)
  • 2011
The concept of Hysteresis Thresholding is utilized to obtain continuous edges information inRGB color channels and extended the original intensity definition and stability criterion of the MSER method in RGB color space with the acquired curves and indicates that in blur and colourful situations, the method performs better.

Scale-Insensitive MSER Features: A Promising Tool for Meaningful Segmentation of Images

This chapter discusses a segmentation technique based on SIMSER (scale-insensitive maximally stable extremal regions) features, which are a generalization of popular MSER features and relations between semantics-based image annotation and SIMSER features are investigated and illustrated by extensive experiments.

Localizing Polygonal Objects in Man-Made Environments

This thesis proposes a contour-based object detection framework to deal with the detection of polygonal objects, and proposes a generic contour grouping based object detection approach by exploring promising cycles in a line fragment graph.

Improved Maximally Stable Extremal Region detector in color images

An improved MSER detector in color images, which can extract significant increased MSERs, and the results from different spaces are with consistent reliability, and SVM classifier is used to filter theMSERs from H, S and I space separately.

Human skin detection in images by MSER analysis

A successful region detector is introduced, i.e., MSER, into the skin detection by regarding the skin region as the maximally stable extremal region (MSER) and extended to both color and texture analysis to reduce the skinlike regions1.

Car license plate detection based on MSER

A MSER license plate detection method constrained by some priori knowledges of license plate is proposed, and the experimental results show the efficiency and robustness of the proposed method.

CZECH TECHNICAL UNIVERSITY IN PRAGUE DOCTORAL THESIS STATEMENT

It is shown how the movement and target model can be used in a coarse to fine approach solving the trade off between the precision and the range of trackable displacement at different scales must be solved.

Convex Framework for 2D & 3D Image Segmentation Using Shape Constraints

This thesis explores different kinds of shape constraints for interactive medical image segmentation embedded in a convex variational framework, and shows how to decrease user interaction significantly.

Robust analysis of feature spaces: color image segmentation

  • D. ComaniciuP. Meer
  • Computer Science
    Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1997
A general technique for the recovery of significant image features is presented. The technique is based on the mean shift algorithm, a simple nonparametric procedure for estimating density gradients.

Color image segmentation: advances and prospects

Unsupervised Segmentation of Color-Texture Regions in Images and Video

The focus of this work is on spatial segmentation, where a criterion for "good" segmentation using the class-map is proposed and applying the criterion to local windows in theclass-map results in the "J-image," in which high and low values correspond to possible boundaries and interiors of color-texture regions.

A review on image segmentation techniques

A Perceptual Colour Segmentation Algorithm

A Perceptual Colour Segmentation Algorithm Christopher G. Healey and James T. Enns This paper presents a simple method for segmenting colour regions into categories like red, green, blue, and yellow.

A novel performance evaluation method of local detectors on non-planar scenes

  • F. FraundorferH. Bischof
  • Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops
  • 2005
The experiments reveal that the results differ from that of previous evaluations on planar scenes, especially that repeatability and matching scores will be much lower in real applications as suggested by previous evaluations.

A New Slice-Based Concept for 3D Paper Structure Analysis Applied to Spatial Coating Layer Formation

Initial experiments on analyzing coated paper samples prove the applicability of the new segmentation concept, based on a fully automated microtomy process and light microscopy, as a first example of possible applications.

Skin-Color Modeling and Adaptation

An adaptive model is proposed to characterize human skin-color distributions for tracking human faces under different lighting conditions based on the maximum likelihood criterion and has been successfully applied to a real-time face tracker and other applications.

Comparison of affine-invariant local detectors and descriptors

Recent progress on local photometric invariants is summarized, which shows that the ranking of the detectors and descriptors remains the same regardless of the scene type or image transformation.