The image foresting transform: theory, algorithms, and applications

By Alexandre Xavier Falcão, Jorge Stolfi, Roberto de Alencar Lotufo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004

635 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a83e9a3dce59292d7dbdab2a8dd20c6b73db3005

How researchers see this paper

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

Citations in the corpus

Power Watershed: A Unifying Graph-Based Optimization Framework (2011, methodology): “, the cases optimized by graph cuts, shortest path forests, and maximum spanning forest algorithms (and watershed in general [12], [26], [13], [71], [34]) have the problem that the optimum solution may not be unique, for example, on plateaus.”
Digital Topology and Geometry in Medical Imaging: A Survey (2015, methodology): “The image foresting transform [161], [162] offers a unified graph-based framework for realization of various connectivity-based operators, including region growing, ordered propagation, watershed, flooding, geodesic dilation, morphological reconstruction etc.”
Supervised pattern classification based on optimum‐path forest (2009, methodology): “The IFT algorithm is essentially Dijkstra’s algorithm (Cormen et al., 1990) modified for multiple sources and more general path-value functions (Falcão et al., 2004).”
Segmentation (2019, methodology): “Variants of the algorithm can be implemented with different tie-breaking policies for nodes in Q [4, 9].”
BBA: A Binary Bat Algorithm for Feature Selection (2012, methodology): “The main difference relies on the fact that OPF uses a set of source nodes (prototypes) with any smooth path-cost function [19].”
User-Friendly Interactive Image Segmentation Through Unified Combinatorial User Inputs (2010, unknown): “Another class of algorithms [17] uses the image foresting transform (IFT) to provide a common framework for interactive boundary-based segmentation such as [7], [18] and interactive region-based segmentation such as different types of watersheds”
Minimum Barrier Salient Object Detection at 80 FPS (2015, background): “However, it is shown in [30] that the MBD transform cannot be exactly solved by Dijkstra-like Algorithms due to the non-smoothness property [11] of the MBD.”
2D Euclidean distance transform algorithms: A comparative survey (2008, methodology): “Up to this date, the EDT by IFT is equivalent to the PSN algorithm and, therefore, is not exact.”
Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach (2006, methodology): “The underlying shortest-path formulation of all these approaches has been revealed and generalized by the Image Foresting Transform (IFT) proposed by Falcão et al. [24].”