Segmentation Based Interest Points and Evaluation of Unsupervised Image Segmentation Methods

Koniusz, Piotr; Mikolajczyk, Krystian

doi:10.5244/c.23.24

Cited by 17 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Segmentation, like edge detection, has often been considered an abstraction mechanism that is not stable enough for the purpose of repeatable region detection. The recent experiments of Koniusz and Mikolajczyk [21] do not look promising either. Higher-level tasks typically combine multiple segmentations [22].…”

Section: Related Workmentioning

confidence: 97%

Detecting Regions from Single Scale Edges

Rapantzikos

Avrithis

Kollias

2012

Trends and Topics in Computer Vision

View full text Add to dashboard Cite

Abstract. We believe that the potential of edges in local feature detection has not been fully exploited and therefore propose a detector that starts from single scale edges and produces reliable and interpretable blob-like regions and groups of regions of arbitrary shape. The detector is based on merging local maxima of the distance transform guided by the gradient strength of the surrounding edges. Repeatability and matching score are evaluated and compared to state-of-the-art detectors on standard benchmarks. Furthermore, we demonstrate the potential application of our method to wide-baseline matching and feature detection in sequences involving human activity.

show abstract

Section: Related Workmentioning

confidence: 97%

Detecting Regions from Single Scale Edges

Rapantzikos

Avrithis

Kollias

2012

Trends and Topics in Computer Vision

View full text Add to dashboard Cite

show abstract

“…A survey on interest points based on Watershed, Mean shift and Graph-cut segmentation was presented by [20]. A method is proposed [20] that uses boundaries and centres of gravity of the segments for extracting features.…”

Section: Previous Workmentioning

confidence: 99%

Segmentation Based Features for Wide-Baseline Multi-view Reconstruction

Mustafa

Kim

Imre

et al. 2015

2015 International Conference on 3D Vision

View full text Add to dashboard Cite

A common problem in wide-baseline stereo is the sparse and non-uniform distribution of correspondences when using conventional detectors such as SIFT, SURF, FAST and MSER. In this paper we introduce a novel segmentation based feature detector SFD that produces an increased number of 'good' features for accurate wide-baseline reconstruction. Each image is segmented into regions by over-segmentation and feature points are detected at the intersection of the boundaries for three or more regions. Segmentation-based feature detection locates features at local maxima giving a relatively large number of feature points which are consistently detected across wide-baseline views and accurately localised. A comprehensive comparative performance evaluation with previous feature detection approaches demonstrates that: SFD produces a large number of features with increased scene coverage; detected features are consistent across wide-baseline views for images of a variety of indoor and outdoor scenes; and the number of wide-baseline matches is increased by an order of magnitude compared to alternative detector-descriptor combinations. Sparse scene reconstruction from multiple wide-baseline stereo views using the SFD feature detector demonstrates at least a factor six increase in the number of reconstructed points with reduced error distribution compared to SIFT when evaluated against ground-truth and similar computational cost to SURF/FAST.

show abstract

“…While there is a significant body of work around suitable evaluation measures for foregroundbackground segmentation [9,14,20], we do not review them in this paper, as we focus on semantic segmentation whose evaluation has been less studied by far.…”

Section: Evaluation Measuresmentioning

confidence: 99%

What is a good evaluation measure for semantic segmentation?

Csurka

Larlus

Perronnin

2013

Procedings of the British Machine Vision Conference 2013

394

264

View full text Add to dashboard Cite

In this work, we consider the evaluation of the semantic segmentation task. We discuss the strengths and limitations of the few existing measures, and propose new ways to evaluate semantic segmentation. First, we argue that a per-image score instead of one computed over the entire dataset brings a lot more insight. Second, we propose to take contours more carefully into account. Based on the conducted experiments, we suggest best practices for the evaluation. Finally, we present a user study we conducted to better understand how the quality of image segmentations is perceived by humans.

show abstract

Segmentation Based Interest Points and Evaluation of Unsupervised Image Segmentation Methods

Cited by 17 publications

References 22 publications

Detecting Regions from Single Scale Edges

Detecting Regions from Single Scale Edges

Segmentation Based Features for Wide-Baseline Multi-view Reconstruction

What is a good evaluation measure for semantic segmentation?

Contact Info

Product

Resources

About