Use of watersheds in contour detection

By Serge Beucher. 1979

Subfields: Computer Vision and Pattern Recognition

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

Deep Watershed Transform for Instance Segmentation (2016, background): “Its application to image segmentation can be traced back to the 70’s [4, 3].”
The Watershed Transform: Definitions, Algorithms and Parallelization Strategies (2000, methodology): “In grey scale mathematical morphology the watershed transform, originally proposed by Digabel and Lantuéjoul [9,20] and later improved by Beucher and Lantuéjoul [4], is the method of choice for image segmentation [5, 46, 52].”
Multiscale X-ray tomography of cementitious materials: A review (2020, methodology): “When connectivity analysis fails to discriminate the various features of the image, the watershed transform can be used [183, 184].”
Self-Supervised Learning via Conditional Motion Propagation (2019, methodology): “We adopt a watershed-based [4] method to sample such key-points.”
Digital Topology and Geometry in Medical Imaging: A Survey (2015, background): “Watershed-based image segmentation was introduced by Beucher and Lantuéjoul [11], and early works were reported in [58], [152]–[154].”
A comparison of three image-object methods for the multiscale analysis of landscape structure (2003, methodology): “MCS is a watershed transformation technique that detects regional similarities as opposed to an edgebased technique that detects local changes (Beucher and Lantuéjoul, 1979; Meyer and Beucher, 1990).”
A review of automatic mass detection and segmentation in mammographic images (2010, unknown): “The watershed transform is a mathematical morphological approach to image segmentation (Beucher and Lenteuejoul, 1979; Vincent and Soille, 1991).”
Generation and Evaluation of a Cortical Area Parcellation from Resting-State Correlations. (2016, methodology): “At this point, instead of using nonmaxima suppression to identify boundaries in the gradient maps, as in Wig, Laumann, Petersen (2014), we used the “watershed by flooding” algorithm (Beucher and Lantuejoul 1979), implemented using custom Matlab scripts.”
A new approach for the morphological segmentation of high-resolution satellite imagery (2001, methodology): “[9] S. Beucher and C. Lantuejoul, “Use of watersheds in contour detection,” in Int.”
Evaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images (2018, methodology): “One of the most commonly used strategies for nucleus segmentation is Otsu ’ s thresholding method (7) followed by seeded watershed (8,9), because of its effectiveness, simplicity of use and computational ef ﬁ ciency.”
The persistent cosmic web and its filamentary structure I: Theory and implementation (2010, methodology): “The watershed technique (see Beucher & Lantujoul 1979; Roerdink & Meijster 2000) was first applied to this kind of problem by Platen et al. (2007) as a means of identifying voids in large-scale structures (see also Platen, van de Weygaert & Jones 2008; Colberg et al. 2008; Aragón-Calvo et al.…”
Computer vision for high content screening (2016, background): “Watershed thresholding (Serge & Lantue´j, 1979) treats a gray-scale image as a topographical map, where pixel intensity indicates elevation and dimmer regions between intensity peaks or previously identified seed regions are defined as boundaries.”
Precision functional mapping of individual human brains (2017, unknown): “Edges were identified in each of the resulting gradient maps using the watershed edge detection technique (Beucher and Lantuejoul, 1979), and all resulting edge maps were summed.”
Prediction of urban human mobility using large-scale taxi traces and its applications (2012, methodology): “The watershed algorithm is a traditional image processing technique to segment an image [22].”
Modeling of organic light emitting diodes: From molecular to device properties (2015, methodology): “Efficient coarsening methods that retain physically sensible trajectories are the stochastic watershed algorithm [109, 114, 115], which is an improved version of the watershed algorithm [116, 117], and a graph-theoretic decomposition [118].”
The Imaging of Dynamic Multiphase Fluid Flow Using Synchrotron-Based X-ray Microtomography at Reservoir Conditions (2015, methodology): “A separate pore was then defined for each of the catchment basins generated by running the watershed algorithm on this distance map (Beucher and Lanteujoul 1979; Wildenschild and Sheppard 2013).”
Segmentation and classification of hyperspectral images using watershed transformation (2010, methodology): “It was introduced in image analysis by Beucher and Lantuéjoul [47], and subsequently a lot of algorithms for its implementation have been proposed.”