Thirty Years Of Graph Matching In Pattern Recognition

By Donatello Conte, Pasquale Foggia, Carlo Sansone, Mario Vento. International journal of pattern recognition and artificial intelligence, 2004

1,573 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f3ab61d9faace6cfffcfc89503c0b804206d9641

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Global Hypothesis Generation for 6D Object Pose Estimation (2016, background): “[4, 27]) is another formalism used to find true correspondences from a large number of hypothetic correspondences using geometric constraints.”
Efficient Algorithms for Detecting Signaling Pathways in Protein Interaction Networks (2005, background): “This problem is distinct from that of finding a path in G that somehow matches a given query path P , as in Zheng et al. (2002) (or, more generally, subgraph matching [Conte et al., 2004]).”
Approximate graph edit distance computation by means of bipartite graph matching (2009, methodology): “…at ScienceDirect Image and Vision Computing journal homepage: www.elsevier .com/locate / imavis Approximate graph edit distance computation by means of bipartite graph matching Kaspar Riesen *, Horst Bunke Institute of Computer Science and Applied Mathematics, University of Bern,…”
The Index-Based Subgraph Matching Algorithm (ISMA): Fast Subgraph Enumeration in Large Networks Using Optimized Search Trees (2013, background): “The discovery and analysis of network motifs crucially depends on the ability to enumerate all instances of a given query subgraph in a network or graph of interest, a classical problem in pattern recognition [7], that is known to be NP complete [8].”
Feature Correspondence Via Graph Matching: Models and Global Optimization (2008, background): “Graph matching optimization Graph matching is a challenging optimization problem which received considerable attention in the literature (see [27] for a comprehensive survey of methods).”
Recent methods and databases in vision-based hand gesture recognition: A review (2015, background): “However, the use of graphs in computer vision and pattern recognition obtained a growing attention from the research community recently, as the computational cost of the graph-based algorithms is now becoming compatible with the computational power of new generation computers [74].”
Probabilistic graph and hypergraph matching (2008, background): “For an overview of recent literature, we refer the reader to a number of special issues that appeared on the subject [1, 2, 3] and the survey article [7].”
A Path Following Algorithm for the Graph Matching Problem (2008, background): “A good review of graph matching algorithms may be found in [25].”
The Graph Neural Network Model (2009, neutral): “Even if the performance of our method is not comparable in terms of best accuracy on the same problem with the most efficient algorithms in the literature, the proposed approach is a very general technique that can be applied on extension of the subgraph matching problems [73]–[75].”
Similarity Search in Graph Databases: A Multi-Layered Indexing Approach (2017, background): “In pattern recognition and computer vision, graphs representing hand-written symbols, fingerprints, or medical images are matched and retrieved approximately for identity discovery, object detection, and scene identification [10], [4].”
Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering (2014, background): “The relation to other hierarchical approaches is also beneficial, given the many successful hierarchical approaches in computer vision, from the classifier cascades used for face detection [46], the Part-Based Model and Latent SVMs [12] applied to general object category detection, Conditional Rando”
Graph Based Shapes Representation and Recognition (2007, background): “…concludes that, it does not exit an algorithm that is definitely better than all others and it depend on graph type e.g., Naughty algorithm perform better for randomly connected graphs of quite large size, while for sparse graphs or more regular graphs like 2D meshes, VF2 is the best algorithm[13].”
Quantification of network structural dissimilarities (2017, methodology): “7b, in which we compare distances between the Power Grid network with networks generated by dk model and also with an fBm (H ¼ 0.14) network (see Supplementary Note 9).”