Stopping Region-Based Image Segmentation at Meaningful Partitions

Adamek, Tomasz; O’Connor, Noel E.

doi:10.1007/978-3-540-77051-0_2

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other techniques incorporate, apart from color and size, contour complexity of the region into the merging criterion (Mumford, 1989), for instance, based on the perimeter length or area-perimeter ratio (Pardas, 1994;Dorea, 2009). In turn, some researchers have tried to emulate human perceptual grouping using more complex criteria, for instance defining syntactic features (Bennstrom, 2005;Adamek, 2007a), such as adjacency, regularity, or inclusion.…”

Section: Region Merging Techniquesmentioning

confidence: 99%

Image Analysis and Understanding Based on Information Theoretical Region Merging Approaches for Segmentation and Cooperative Fusion

Calderero

Marqués

2013

Handbook of Research on Computational Intelligence for Engineering, Science, and Business

View full text Add to dashboard Cite

This chapter addresses the automatic creation of simplified versions of the image, known as image segmentation or partition, preserving the most semantically relevant information of the image at different levels of analysis. From a semantic and practical perspective, image segmentation is a first and key step for image analysis and pattern recognition since region-based image representations provide a first level of abstraction and a reduction of the number of primitives, leading to a more robust estimation of parameters and descriptors. The proposed solution is based on an important class of hierarchical bottom-up segmentation approaches, known as region merging techniques. These approaches naturally provide a bottom-up hierarchy, more suitable when no a priori information about the image is available, and an excellent compromise between efficiency of computation and representation. The chapter is organized in two parts dealing with the following objectives: (i) provide an unsupervised solution to the segmentation of generic images; (ii) design a generic and scalable scheme to automatically fuse hierarchical segmentation results that increases the robustness and accuracy of the final solution.

show abstract

Section: Region Merging Techniquesmentioning

confidence: 99%

Image Analysis and Understanding Based on Information Theoretical Region Merging Approaches for Segmentation and Cooperative Fusion

Calderero

Marqués

2013

Handbook of Research on Computational Intelligence for Engineering, Science, and Business

View full text Add to dashboard Cite

show abstract

“…In [49], a stopping criterion based on the evolution of the accumulated merging cost during the overall process is proposed. Its goal is to extract the most salient semantic regions or objects present in the scene.…”

Section: A Stopping Criterion Versus Selection Criterionmentioning

confidence: 99%

Region Merging Techniques Using Information Theory Statistical Measures

Calderero

Marqués

2010

IEEE Trans. on Image Process.

117

View full text Add to dashboard Cite

Abstract-The purpose of the current work is to propose, under a statistical framework, a family of unsupervised region merging techniques providing a set of the most relevant region-based explanations of an image at different levels of analysis. These techniques are characterized by general and nonparametric region models, with neither color nor texture homogeneity assumptions, and a set of innovative merging criteria, based on information theory statistical measures. The scale consistency of the partitions is assured through i) a size regularization term into the merging criteria and a classical merging order, or ii) using a novel scale-based merging order to avoid the region size homogeneity imposed by the use of a size regularization term. Moreover, a partition significance index is defined to automatically determine the subset of most representative partitions from the created hierarchy. Most significant automatically extracted partitions show the ability to represent the semantic content of the image from a human point of view. Finally, a complete and exhaustive evaluation of the proposed techniques is performed, using not only different databases for the two main addressed problems (object-oriented segmentation of generic images and texture image segmentation), but also specific evaluation features in each case: under-and oversegmentation error, and a large set of region-based, pixel-based and error consistency indicators, respectively. Results are promising, outperforming in most indicators both object-oriented and texture state-of-the-art segmentation techniques.

show abstract

“…After the challenge, it has been demonstrated [11] that the segmentation accuracy could be markedly improved by re-segmenting the bounding boxes of our detections. Hierarchical segmentation methods have been studied quite much lately [1,14] and it might be beneficial to update our segmentation method according to recent findings.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Techniques for Image Classification, Object Detection and Object Segmentation

Viitaniemi¹,

Laaksonen²

Visual Information Systems. Web-Based Visual Information Search and Management

View full text Add to dashboard Cite

ABSTRACT:In this paper we document the techniques which we used to participate in the PASCAL NoE VOC Challenge 2007 image analysis performance evaluation campaign. We took part in three of the image analysis competitions: image classification, object detection and object segmentation. In the classification task of the evaluation our method produced comparatively good performance, the 4th best of 19 submissions. In contrast, our detection results were quite modest. Our method's segmentation accuracy was the best of all submissions. Our approach for the classification task is based on fused classifications by numerous global image features, including histograms of local features. The object detection combines similar classification of automatically extracted image segments and the previously obtained scene type classifications. The object segmentations are obtained in a straightforward fashion from the detection results.

show abstract

Stopping Region-Based Image Segmentation at Meaningful Partitions

Cited by 5 publications

References 22 publications

Image Analysis and Understanding Based on Information Theoretical Region Merging Approaches for Segmentation and Cooperative Fusion

Image Analysis and Understanding Based on Information Theoretical Region Merging Approaches for Segmentation and Cooperative Fusion

Region Merging Techniques Using Information Theory Statistical Measures

Techniques for Image Classification, Object Detection and Object Segmentation

Contact Info

Product

Resources

About