Recognition of shapes by editing their shock graphs

By Thomas B. Sebastian, Philip N. Klein, Benjamin B. Kimia. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004

782 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f6825e12c1a8a78068fdff8581279faa4c7b7781

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

Learning Context-Sensitive Shape Similarity by Graph Transduction (2010, methodology): “It appears to us that many published shape distance measures [1], [ 2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14] are unable to address this issue.”
Shape Classification Using the Inner-Distance (2007, background): “In contrast, the other two categories (e.g. [23], [4], [39], [41], [17], [30], etc.) capture part structures from only one image.”
Hierarchical Matching of Deformable Shapes (2007, methodology): “In classification tasks, we obtain better recognition results than other methods on several shape datasets, including the MPEG-7 shape dataset [15], a Swedish leaf dataset [26], and a silhouette dataset from Brown University [24].”
50 Years of object recognition: Directions forward (2013, background): “More recent work has expanded the scope of graph based algorithms using shock graphs [181], [210], [211], [212], [213], [214], [215].”
A Similarity-Based Aspect-Graph Approach to 3D Object Recognition (2004, methodology): “We expect that the differences in the curve-based and shock-based metric would become more significant with larger databases due to the superior discrimination capability of shock-based matching (Sebastian and Kimia, 2001; Sebastian et al., 2002, 2004 ).”
Active skeleton for non-rigid object detection (2009, background): “The idea of using skeleton (medial axis) to model the object shape has been extensively studied in the literature [6, 2, 36, 24, 19, 21, 18].”
A survey of graph edit distance (2010, methodology): “Inexact graph matching has been successfully applied to recognition of characters [6, 7], shape analysis [8, 9], image and video indexing [10–14] and image registration [15].”
Shape retrieval using triangle-area representation and dynamic space warping (2007, methodology): “The shock graph edit (SGE) method [30] breaks down a shape’s skeleton into parts (or shocks) and represents them as graph nodes and their relations as graph edges; thus, it handles partial occlusions explicitly.”
Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs (2016, background): “Skeleton extraction from pre-segmented images [23] used to be a hot topic, which has been well studied and successfully applied to shape-based object matching and recognition [27, 24, 9].”
Retrieving Articulated 3-D Models Using Medial Surfaces and Their Graph Spectra (2005, methodology): “object indexing and matching using 2-D skeletal graphs [28, 25, 18, 22].”