Contour-based partial object recognition using symmetry in image databases

Cho, June-Suh; Choi, Ji-Hyun

doi:10.1145/1066677.1066947

Cited by 9 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In computer vision experiments, researcher usually work with invisible occluding patterns, both on outlines (see, e.g., [4,13,19,21,22]) and on filled shapes (see, e.g., [15]). …”

Section: Shape Recognition In the Presence Of Occlusionsmentioning

confidence: 99%

“…Basically, the interest in robustness against partial occlusions is motivated by the problem of recognizing an object partially hidden by some other foreground object in the same image. The ability to recognize shapes, even when they are partially occluded by another pattern, has been investigated in the Computer Vision literature by various authors, with reference to a variety of shape recognition methods (see, e.g., [4,13,15,19,21,22]). We experimentally show that the ranks of the 0th degree persistent homology groups, also known as size function [11], are able to preserve local information, so that they can manage uncertainty due to the presence of occluded shapes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Mayer–Vietoris Formula for Persistent Homology with an Application to Shape Recognition in the Presence of Occlusions

Fabio

Landi

2011

Found Comput Math

View full text Add to dashboard Cite

In algebraic topology it is well-known that, using the Mayer-Vietoris sequence, the homology of a space X can be studied splitting X into subspaces A and B and computing the homology of A, B, A ∩ B. A natural question is to which an extent persistent homology benefits of a similar property. In this paper we show that persistent homology has a Mayer-Vietoris sequence that in general is not exact but only of order two. However, we obtain a Mayer-Vietoris formula involving the ranks of the persistent homology groups of X, A, B and A ∩ B plus three extra terms. This implies that topological features of A and B either survive as topological features of X or are hidden in A ∩ B. As an application of this result, we show that persistence diagrams are able to recognize an occluded shape by showing a common subset of points.

show abstract

“…In computer vision experiments, researcher usually work with invisible occluding patterns, both on outlines (see, e.g., [4,13,19,21,22]) and on filled shapes (see, e.g., [15]). …”

Section: Shape Recognition In the Presence Of Occlusionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Mayer–Vietoris Formula for Persistent Homology with an Application to Shape Recognition in the Presence of Occlusions

Fabio

Landi

2011

Found Comput Math

View full text Add to dashboard Cite

show abstract

“…By defining relation vector space which can describe the structural information of an object centered at specific feature, the labels of objects are only affected by the binary relation vectors of features. Cho [6] reconstructed the partial shapes based on symmetry. His method is only suit for the objects which are symmetry and whose section is ellipse or approximately circle.…”

Section: Introductionmentioning

confidence: 99%

Recognizing Partially Occluded Object from a Line Drawing

Zhang¹,

Chu²

2011

JCP

View full text Add to dashboard Cite

Most existing methods for partially occluded object recognition are only suit for Euclid and similarity transformation. As a result, the performance would be degraded in the affine and perspective transformation. This paper focuses on partially occluded shape recognition under affine transformation. The recognition algorithms are as follows: First, a new local invariant under affine transformation is given based on the invariants in affine geometry. Second, a new similarity function is established to measure the similarity between models and object to be recognized on the basis of the local invariant. And then, a transform function is designed to normalize the similarity value between 0 and 1, so it is convenient to select similarity threshold. Finally, a loss feature judged function is constructed to judge whether each local feature is lost, and similarity is calculated only use the local features which are not lost. By comparing similarity with pre-threshold, we can recognize object from a partially occluded line drawing. The similarity function and the loss feature judge function consider the noises and occlusion. As a result, the reliability of recognition is improved greatly. The experiment results show that the proposed algorithms are quite robust to shape variations, including noise and occlusion. Moreover, they establish one-to-one correspondence between model features and object features in a scene, and can recognize multiple objects.

show abstract