Yet Another Survey on Image Segmentation: Region and Boundary Information Integration

By Jordi Freixenet, Xavier Muñoz, D. Raba, Joan Martí, X. Cufí. European Conference on Computer Vision, 2002

605 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/954da573e1268c43480684d5c59e89f8d8f3ce42

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Object‐based land‐cover classification for the Phoenix metropolitan area: optimization vs. transportability (2008, background): “2.5 Segmentation While many different segmentation algorithms exist (Pal and Pal 1993, Freixenet et al. 2002, Blaschke et al. 2004), there are very few operational software environments for the processing of remotely sensed data (for a comparison, see Meinel and Neubert 2004).”
What is a good evaluation measure for semantic segmentation? (2013, neutral): “Popular contour-based measures for unsupervised segmentation include the Berkeley contour matching score [14] and the Boundary Displacement Error [5] (BDE).”
Learning to Detect A Salient Object (2007, methodology): “For the boundary-based measurement, we use boundary displacement error (BDE) [5], which measures the average displacement error of corresponding boundaries of two rect-angles.”
A review of automatic mass detection and segmentation in mammographic images (2010, methodology): “As Freixenet et al. (2002) reviewed, this information can be introduced before the growing step, using for example a controlled seed placement (Benois and Barba, 1992) or during growing, like in active region algorithms (Zhu and Yuille, 1996).”
Toward Objective Evaluation of Image Segmentation Algorithms (2007, background): “Boundary matching: Several measures work by matching boundaries between the segmentations, and computing some summary statistic of match quality [7], [8].”
Understanding Deep Learning Techniques for Image Segmentation (2019, methodology): “While some of them specialized in application areas [107, 123, 185], while other focused on specific types of algorithms [20, 19, 59].”
Real-time clothing recognition in surveillance videos (2011, methodology): “We develop a lightweight variant of the region growing based color segmentation method [12] for foreground clothing segmentation.”
Unsupervised segmentation of natural images via lossy data compression (2008, background): “The GCE and BDE indices penalize undersegmentation more heavily than oversegmentation.”
Change detection from remotely sensed images: From pixel-based to object-based approaches (2013, neutral): “Most of the segmentation approaches can be grouped into either boundary or edge-based (discontinuity of pixels) or areabased (similarity of pixels) techniques (Freixenet et al., 2002).”
A survey of graph theoretical approaches to image segmentation (2013, methodology): “To quantitatively evaluate the segmentation results, as in [133-134]) we use five well-known indices: Probabilistic Rand (PR) index [107], Normalized Probabilistic Rand (NPR) index [107], Variation of Information (VI) [131], Global Consistency Error (GCE) [106] and Boundary Displacement Error (BDE) ”