Shape Matching Using Point Context and Contour Segments

Feinen, Christian; Yang, Cong; Tiebe, Oliver; Grzegorzek, Marcin

doi:10.1007/978-3-319-16817-3_7

Cited by 4 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Together with the distances, a single point of interest pi is encoded in two ndimensional vectors D p i and Θ p i . Our proposed point descriptor differs from the methods [5] and [3] in the following aspects. Firstly, we only consider the feature vectors from points of interest instead of roughly uniform spacing or randomly picking for selecting sample points.…”

Section: Point Contextmentioning

confidence: 96%

“…Secondly, the proposed point descriptor is naturally translation and rotation invariant 1 . However, approaches in [5,3] are not intrinsically rotation invariant. In order to solve this problem, they use the tangent angle on each point to turn the shape.…”

Section: Point Contextmentioning

confidence: 98%

“…In this section an approach [5] is employed on an arbitrary given shape Ω to select boundary points pi which are significant for the perceptual appearance. The general idea is to detect contour regions like the legs or the tail of an elephant characterised by a higher curvature toward the overall shape trend.…”

Section: Points Of Interestmentioning

confidence: 99%

“…However, most existing methods [10,1,6] only consider the relationship between single points in different objects. This could lead to ambiguous matching because many different points may have similar descriptors [5,13]. It has been shown that high-order graph matching is a powerful framework to establish feature correspondences, combining both appearance similarity and geometric compatibility [12].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Shape-based Object Matching Using Point Context

Yang

Feinen

Tiebe

et al. 2015

Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel object matching algorithm based on shape contours. In order to ensure low computational complexity in shape representation, our descriptor is composed by a small number of interest points which are generated by considering both curvatures and the overall shape trend. To effectively describe each point of interest, we introduce a simple and highly discriminative point descriptor, namely Point Context, which represents its geometrical and topological location. For shape matching, we observed that the correspondences are not only dependent on the similarities between these single points in different objects, but they are also related to the geometric relations between multiple points of interest in the same object. Therefore, a high-order graph matching formulation is introduced to merge the single point similarities and the similarities between point triangles. The main contributions of this paper include (i) the introduction of a novel shape descriptor with robust shape points and their descriptors and (ii) the implementation of a high-order graph matching algorithm that solves the shape matching problem. Our method is validated through a series of object retrieval experiments on four datasets demonstrating its robustness and accuracy.

show abstract

Section: Point Contextmentioning

confidence: 96%

Section: Point Contextmentioning

confidence: 98%

Section: Points Of Interestmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Shape-based Object Matching Using Point Context

Yang

Feinen

Tiebe

et al. 2015

Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kimia (2003) presented the validity of skeletons from the psychophysical and neurophysiological perspectives. Also, researchers are exploring methods that recognize objects by appropriately matching parts of their skeletons (Bai & Latecki, 2008;Feinen, Yang, Tiebe, & Grzegorzek, 2014). Furthermore, these methods are being extended to realistic images with cluttered backgrounds, where an object is detected by applying contours of its parts to edges extracted for an image (Bai, Wang, Latecki, Liu, & Tu, 2009).…”

Section: Cognitive Approachesmentioning

confidence: 99%

Human-Machine Cooperation in Large-Scale Multimedia Retrieval: A Survey

Shirahama¹,

Grzegorzek²,

Indurkhya³

2015

The Journal of Problem Solving

Self Cite

View full text Add to dashboard Cite

Large-Scale Multimedia Retrieval (LSMR) is the task to fast analyze a large amount of multimedia data like images or videos and accurately find the ones relevant to a certain semantic meaning. Although LSMR has been investigated for more than two decades in the fields of multimedia processing and computer vision, a more interdisciplinary approach is necessary to develop an LSMR system that is really meaningful for humans. To this end, this paper aims to stimulate attention to the LSMR problem from diverse research fields. By explaining basic terminologies in LSMR, we first survey several representative methods in chronological order. This reveals that due to prioritizing the generality and scalability for large-scale data, recent methods interpret semantic meanings with a completely different mechanism from humans, though such humanlike mechanisms were used in classical heuristic-based methods. Based on this, we discuss human-machine cooperation, which incorporates knowledge about human interpretation into LSMR without sacrificing the generality and scalability. In particular, we present three approaches to human-machine cooperation (cognitive, ontological, and adaptive), which are attributed to cognitive science, ontology engineering, and metacognition, respectively. We hope that this paper will create a bridge to enable researchers in different fields to communicate about the LSMR problem and lead to a ground-breaking next generation of LSMR systems.

show abstract

Occluded Leaf Matching with Full Leaf Databases Using Explicit Occlusion Modelling

Chaudhury

Barron

2018

2018 15th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

Shape Matching Using Point Context and Contour Segments

Cited by 4 publications

References 22 publications

Shape-based Object Matching Using Point Context

Shape-based Object Matching Using Point Context

Human-Machine Cooperation in Large-Scale Multimedia Retrieval: A Survey

Occluded Leaf Matching with Full Leaf Databases Using Explicit Occlusion Modelling

Contact Info

Product

Resources

About