Benchmarking Image Segmentation Algorithms

Estrada, Francisco José Pozuelos; Jepson, Allan D.

doi:10.1007/s11263-009-0251-z

Cited by 151 publications

(78 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 1:1 matching is possible by adding outlier nodes. Any match to an outlier or beyond some distance threshold is counted as a mismatch.In a recent variation on this approach (E-PR), Estrada et al [6] include 'no intervening contours' and 'same side' constraints. While these constraints serve to encourage ordering consistency between the two contours being matched, neither approach strictly enforces ordering consistency in a global sense.…”

Section: Precision-recall Analysismentioning

confidence: 99%

Design and perceptual validation of performance measures for salient object segmentation

Movahedi

Elder

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops

395

191

View full text Add to dashboard Cite

show abstract

Section: Precision-recall Analysismentioning

confidence: 99%

Design and perceptual validation of performance measures for salient object segmentation

Movahedi

Elder

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops

395

191

View full text Add to dashboard Cite

show abstract

“…We used the EDISON software which is an improvement of the mean shift [20]. A graph-cut and normalized-cut that are popularly used due to their performance and publicly available source codes were already evaluated to be slower than the mean shift by [8].…”

Section: Resultsmentioning

confidence: 99%

“…Image segmentation has a long history in computer vision [8]. One of the most prominent recent trends is to make objective the evaluation of segmentation results [9][10].…”

Section: Related Workmentioning

confidence: 99%

Multi-scale Image Segmentation Using MSER and its Application

Lee¹,

Oh²

2014

The Journal of the Korea Contents Association

View full text Add to dashboard Cite

Multi-scale image segmentation is important in many applications such as image stylization and medical diagnosis. This paper proposes a novel segmentation algorithm based on MSER(maximally stable extremal region) which captures multi-scale structure and is stable and efficient. The algorithm collects MSERs and then partitions the image plane by redrawing MSERs in specific order. To denoise and smooth the region boundaries, hierarchical morphological operations are developed. To illustrate effectiveness of the algorithm's multi-scale structure, effects of various types of LOD control are shown for image stylization. The proposed technique achieves this without time-consuming multi-level Gaussian smoothing. The comparisons of segmentation quality and timing efficiency with mean shift-based Edison system are presented.■ keyword :|Image Segmentation|Image Stylization|Morphology|Multi-scale|

show abstract

“…The seven metrics utilized to evaluate CLEG and the compared algorithms are computation time (time), completeness (comp), correctness (corr) [49], reference cross-lap (RCL), detection cross-lap (DCL) [50,51], boundary precision (BP), and boundary recall (BR) [52].…”

Section: Roof Segmentationmentioning

confidence: 99%

Fast and Accurate Plane Segmentation of Airborne LiDAR Point Cloud Using Cross-Line Elements

2016

Remote Sensing

View full text Add to dashboard Cite

Plane segmentation is an important step in feature extraction and 3D modeling from light detection and ranging (LiDAR) point cloud. The accuracy and speed of plane segmentation are two issues difficult to balance, particularly when dealing with a massive point cloud with millions of points. A fast and easy-to-implement algorithm of plane segmentation based on cross-line element growth (CLEG) is proposed in this study. The point cloud is converted into grid data. The points are segmented into line segments with the Douglas-Peucker algorithm. Each point is then assigned to a cross-line element (CLE) obtained by segmenting the points in the cross-directions. A CLE determines one plane, and this is the rationale of the algorithm. CLE growth and point growth are combined after selecting the seed CLE to obtain the segmented facets. The CLEG algorithm is validated by comparing it with popular methods, such as RANSAC, 3D Hough transformation, principal component analysis (PCA), iterative PCA, and a state-of-the-art global optimization-based algorithm. Experiments indicate that the CLEG algorithm runs much faster than the other algorithms. The method can produce accurate segmentation at a speed of 6 s per 3 million points. The proposed method also exhibits good accuracy.

show abstract

Benchmarking Image Segmentation Algorithms

Cited by 151 publications

References 34 publications

Design and perceptual validation of performance measures for salient object segmentation

Design and perceptual validation of performance measures for salient object segmentation

Multi-scale Image Segmentation Using MSER and its Application

Fast and Accurate Plane Segmentation of Airborne LiDAR Point Cloud Using Cross-Line Elements

Contact Info

Product

Resources

About