Non-rigid point set registration by preserving global and local structures
In previous work on point registration, the input point sets are often represented using
Gaussian mixture models and the registration is then addressed through a probabilistic …
Gaussian mixture models and the registration is then addressed through a probabilistic …
Sparse contextual activation for efficient visual re-ranking
In this paper, we propose an extremely efficient algorithm for visual re-ranking. By
considering the original pairwise distance in the contextual space, we develop a feature …
considering the original pairwise distance in the contextual space, we develop a feature …
Bag of contour fragments for robust shape classification
Shape representation is a fundamental problem in computer vision. Current approaches to
shape representation mainly focus on designing low-level shape descriptors which are …
shape representation mainly focus on designing low-level shape descriptors which are …
MARCH: Multiscale-arch-height description for mobile retrieval of leaf images
In this paper, we propose a novel shape description method for mobile retrieval of leaf
images. In this method, termed multiscale arch height (MARCH), hierarchical arch height …
images. In this method, termed multiscale arch height (MARCH), hierarchical arch height …
Shape vocabulary: A robust and efficient shape representation for shape matching
In this paper, a learning-based shape descriptor for shape matching is demonstrated.
Formulated in a bag-of-words like framework, the proposed method summarizes the local …
Formulated in a bag-of-words like framework, the proposed method summarizes the local …
Hierarchical string cuts: a translation, rotation, scale, and mirror invariant descriptor for fast shape retrieval
This paper presents a novel approach for both fast and accurately retrieving similar shapes.
A hierarchical string cuts (HSCs) method is proposed to partition a shape into multiple level …
A hierarchical string cuts (HSCs) method is proposed to partition a shape into multiple level …
Multiscale Fourier descriptor based on triangular features for shape retrieval
C Yang, Q Yu - Signal Processing: Image Communication, 2019 - Elsevier
Shape information plays an important role in the human visual system, and how to represent
the shape accurately is a very challenging issue in shape recognition. In recent years, many …
the shape accurately is a very challenging issue in shape recognition. In recent years, many …
A Lie algebra representation for efficient 2D shape classification
Riemannian manifold plays a vital role as a powerful mathematical tool in computer vision,
with important applications in curved shape analysis and classification. Significant progress …
with important applications in curved shape analysis and classification. Significant progress …
Patchy image structure classification using multi-orientation region transform
Exterior contour and interior structure are both vital features for classifying objects. However,
most of the existing methods consider exterior contour feature and internal structure feature …
most of the existing methods consider exterior contour feature and internal structure feature …
A novel method for 2D nonrigid partial shape matching
C Yang, H Wei, Q Yu - Neurocomputing, 2018 - Elsevier
There are two categories of partial shape matching problem: whole-to-part matching and
part-to-part matching. The first establishes the best match between an open curve and a part …
part-to-part matching. The first establishes the best match between an open curve and a part …