Rotation Invariant Non-rigid Shape Matching in Cluttered Scenes

Lian, Wei; Zhang, Lei

doi:10.1007/978-3-642-15555-0_37

Cited by 8 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since CDT can only be used for template matching in images, it is only tested in subsection V-C where images are involved. We also compare MSTT with our previously proposed fan-shaped triangulation (FST) based method [12] in subsection V-A. To make a fair comparison, the deformation regularization terms in FST are changed to the second term in Eq.…”

Section: Resultsmentioning

confidence: 99%

“…In our previous work [12], fan-shaped triangulation was proposed for shape representation to enable SC rotation invariant. It assumes that the model point set resembles the shape of a simple polygon, which is obtained via finding the shortest Hamiltonian cycle [33].…”

Section: Shape Representation Based On Mst Induced Triangulationmentioning

confidence: 99%

“…Similar to the practice in [12], we can reduce the running time of the algorithm based on the following observations. 1) Since the length of a boundary edge (x i , x j ) is small, given location l i , the possible candidates for l j should be the indices of those points near y li (15 nearest points are chosen in our algorithm) because points far from it will introduce severe distortion in the model.…”

Section: E Algorithmmentioning

confidence: 99%

“…MST induced triangulation can be viewed as an improvement over our previously proposed fan-shaped triangulation scheme [12] in order to better handle the case when shapes cannot be easily represented as simple polygons. In such cases, MST is better than simple polygons to represent shapes.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Rotation-Invariant Nonrigid Point Set Matching in Cluttered Scenes

Lian

Zhang

2012

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-This paper addresses the problem of rotation invariant nonrigid point set matching. The shape context (SC) feature descriptor is used because of its strong discriminative nature, while edges in the graphs constructed by point sets are used to determine the orientations of SCs. Like lengths or directions, oriented SCs constructed in this way can be regarded as attributes of edges. By matching edges between two point sets, rotation invariance is achieved. Two novel ways of constructing graphs on model point set are proposed, aiming at making the orientations of SCs as robust to disturbances as possible. The structures of these graphs facilitate the use of dynamic programming (DP) for optimization. The strong discriminative nature of SC, the special structure of the model graphs, and the global optimality of DP make our methods robust to various types of disturbances, particularly clutters. The extensive experiments on both synthetic and real data validated the robustness of the proposed methods to various types of disturbances. They can robustly detect the desired shapes in complex and highly cluttered scenes.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Shape Representation Based On Mst Induced Triangulationmentioning

confidence: 99%

Section: E Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Rotation-Invariant Nonrigid Point Set Matching in Cluttered Scenes

Lian

Zhang

2012

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Since the worst case complexity of our algorithm is exponential, we set the maximum search depth as 3 to make a good trade-off between running time and matching accuracy. We compare our method with 4 state-of-the-art methods: the unified graphical (UG) method [15] where similarity transformation is chosen, the fan-shaped triangulation (FST) method [16], the Viterbi algorithm (VA) based method [17] and the linear programming (LP) based method [14]. These methods can guarantee globally optimal or sub-optimal (for LP) solutions and some of them (UG and FST) are also rotation invariant, making them good candidates for comparison.…”

Section: Where [C D]mentioning

confidence: 99%

Robust Point Matching Revisited: A Concave Optimization Approach

Lian

Zhang

2012

Computer Vision – ECCV 2012

Self Cite

View full text Add to dashboard Cite

Abstract. The well-known robust point matching (RPM) method uses deterministic annealing for optimization, and it has two problems. First, it cannot guarantee the global optimality of the solution and tends to align the centers of two point sets. Second, deformation needs to be regularized to avoid the generation of undesirable results. To address these problems, in this paper we first show that the energy function of RPM can be reduced to a concave function with very few non-rigid terms after eliminating the transformation variables and applying linear transformation; we then propose to use concave optimization technique to minimize the resulting energy function. The proposed method scales well with problem size, achieves the globally optimal solution, and does not need regularization for simple transformations such as similarity transform. Experiments on synthetic and real data validate the advantages of our method in comparison with state-of-the-art methods.

show abstract

Data Graph Formulation as the Minimum-Weight Maximum-Entropy Problem

Sousa

Kropatsch

2015

Graph-Based Representations in Pattern Recognition

View full text Add to dashboard Cite

Rotation Invariant Non-rigid Shape Matching in Cluttered Scenes

Cited by 8 publications

References 24 publications

Rotation-Invariant Nonrigid Point Set Matching in Cluttered Scenes

Rotation-Invariant Nonrigid Point Set Matching in Cluttered Scenes

Robust Point Matching Revisited: A Concave Optimization Approach

Data Graph Formulation as the Minimum-Weight Maximum-Entropy Problem

Contact Info

Product

Resources

About