Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleApril 2023
An efficient region expansion algorithm for regular triangulated meshes
Pattern Recognition Letters (PTRL), Volume 168, Issue CPages 1–7https://doi.org/10.1016/j.patrec.2023.02.014Highlights- Region expansion in regular triangulated meshes can be approximated sublinearly.
- Triangular quadtrees provide efficiency with merging clusters and vertex sets.
- A hexagonal norm provides tightly-bound distance estimates for ...
Region expansion—the growth of regions to include all points within a certain distance of their perimeters—is a basic, widely applicable operation, but is expensive to perform exactly. It has been shown that, if the solution is approximated by ...
- research-articleDecember 2022
Digital geometry on a cubic stair-case mesh
Pattern Recognition Letters (PTRL), Volume 164, Issue CPages 140–147https://doi.org/10.1016/j.patrec.2022.11.003Highlights- The cubic grid Z 3 plays important role in the (digital) world.
- Meshes obtained ...
In this paper, we investigate digital geometry on the rhombille tiling, D(6,3,6,3), that is the dual of the semi-regular tiling called hexadeltille T(6,3,6,3) tiling and also known as trihexagonal tiling. In fact, this tiling can be ...
Graphical abstractTo create your abstract, type over the instructions in the template box below.
Fonts or abstract dimensions should not be changed or altered.
Display Omitted
- rapid-communicationJanuary 2022
High-fidelity 3D face reconstruction with multi-scale details
Pattern Recognition Letters (PTRL), Volume 153, Issue CPages 51–58https://doi.org/10.1016/j.patrec.2021.11.022Highlights- We propose a novel cascaded framework to reconstruct 3D faces with subtle details.
Despite tremendous success has been achieved in faithfully reconstructing face shapes from single images, recovering accurate local details still remains challenging. Previous works propose reprojection-based methods to improve the ...
- research-articleDecember 2021
A maximum diversity-based path sparsification for geometric graph matching
Pattern Recognition Letters (PTRL), Volume 152, Issue CPages 107–114https://doi.org/10.1016/j.patrec.2021.09.019Highlights- Proposes a new dissimilarity measure for geometric graphs.
- Provides a graph ...
This paper presents an effective dissimilarity measure for geometric graphs representing shapes. The proposed dissimilarity measure is a distance that combines a sparsification of the geometric graph based on the maximum diversity ...
- rapid-communicationOctober 2021
Representing point clouds with generative conditional invertible flow networks
Pattern Recognition Letters (PTRL), Volume 150, Issue CPages 26–32https://doi.org/10.1016/j.patrec.2021.07.001Highlights- We propose a novel generative model for 3D point clouds.
- The model utilizes two ...
In this paper, we propose a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. This interpretation matches intrinsic characteristics of point clouds: the ...
-
- rapid-communicationMay 2021
A rotation and scale invariant approach for multi-oriented floor plan image retrieval
Pattern Recognition Letters (PTRL), Volume 145, Issue CPages 1–7https://doi.org/10.1016/j.patrec.2021.01.020Highlights- We have introduced a novel algorithm for outer shape extraction from floor plan images.
Display Omitted
AbstractAn automatic system for analysis and retrieval of building floor plans images is helpful for the architects while designing new projects and providing recommendations to the buyers. For such systems, query by example is preferred over ...
- rapid-communicationFebruary 2021
Convolution operations for relief-pattern retrieval, segmentation and classification on mesh manifolds
Pattern Recognition Letters (PTRL), Volume 142, Issue CPages 32–38https://doi.org/10.1016/j.patrec.2020.11.017Highlights- Two approaches for mesh convolution are proposed: Mesh-Grid and Mesh-Convolution.
Relief patterns represent a surface characteristic that is well distinct from the 3D object shape. They can be seen as the 3D counterpart of the texture concept in the 2D images. A large part of texture analysis, in 2D image state-of-...
- rapid-communicationFebruary 2020
Quick automatic head image matting method based on segmentation and propagation
Pattern Recognition Letters (PTRL), Volume 130, Issue CPages 30–37https://doi.org/10.1016/j.patrec.2019.02.012Highlights- Quick automatic extracting the head photo.
- Need not given tripmap or scribble.
Image matting is a process of extracting objects from background in an image, which is an important work in digital image processing and video editing. Previous methods have poor performance and most methods need trimap or scribble to ...
- rapid-communicationDecember 2019
Augmenting a 3D morphable model of the human head with high resolution ears
Pattern Recognition Letters (PTRL), Volume 128, Issue CPages 378–384https://doi.org/10.1016/j.patrec.2019.09.026Highlights- A new training process for 3D Morphable Models using landmarked 2D data augmentation.
We present a parts-based 3D Morphable Model (3DMM) of the full human head, with particular emphasis on modelling the complex shape of the ear as a flexible, high-resolution separate part. The 3D ear model part undergoes an iterative ...
- rapid-communicationDecember 2019
Connected filters on generalized shape-Spaces
Pattern Recognition Letters (PTRL), Volume 128, Issue CPages 348–354https://doi.org/10.1016/j.patrec.2019.09.018Highlights- We introduce an extension of the tree-based shape-space for segmentation purpose.
Classical hierarchical image representations and connected filters work on sets of connected components (CC). These approaches can be defective to describe the relations between disjoint objects or partitions of images. In practice, ...
- rapid-communicationDecember 2019
Fast and efficient calculations of structural invariants of chirality
Pattern Recognition Letters (PTRL), Volume 128, Issue CPages 270–277https://doi.org/10.1016/j.patrec.2019.09.010Highlights- Chiral invariants before and after reflection are opposite to each other.
- Brief ...
Display Omitted
AbstractChirality describes the structural properties or configuration of an object, and it plays an important role in fields such as physics, chemistry and biology. It is critical to identify achiral objects and determine symmetry plane of ...
- rapid-communicationDecember 2019
Shape description and recognition by implicit Chebyshev moments
Pattern Recognition Letters (PTRL), Volume 128, Issue CPages 137–145https://doi.org/10.1016/j.patrec.2019.08.031Highlights- The definition of Implicit Chebyshev Moments (ICMs) was given.
- The algorithm ...
Chebyshev Moments(CMs) have been applied to representation and recognition of 2D object shapes in image processing and computer vision. However they still suffer from poor representation power and difficulty in computing invariants for ...
- rapid-communicationDecember 2019
Guided thinning
Pattern Recognition Letters (PTRL), Volume 128, Issue CPages 176–182https://doi.org/10.1016/j.patrec.2019.08.030Highlights- Improved condition based on distance map usable in any iterative thinning algorithms.
Display Omitted
AbstractWe present a generic improvement for parallelizable iterative thinning algorithms. The improvement achieves a significant better approximation of the medial axis. The values of a previously computed distance map guide the thinning ...
- research-articleDecember 2019
3D object recognition and pose estimation for random bin-picking using Partition Viewpoint Feature Histograms
Pattern Recognition Letters (PTRL), Volume 128, Issue CPages 148–154https://doi.org/10.1016/j.patrec.2019.08.016Highlights- A novel 3D feature descriptor for object recognition and 6DOF pose estimation is proposed.
3D object recognition and pose estimation are challenging tasks in industrial scenarios. In this paper, we propose an accurate and robust algorithm for object recognition and 6DOF pose estimation for bin-picking applications. We first ...
- rapid-communicationNovember 2019
Ground and aerial meta-data integration for localization and reconstruction: A review
Pattern Recognition Letters (PTRL), Volume 127, Issue CPages 202–214https://doi.org/10.1016/j.patrec.2018.07.036Highlights- Methods of integrating ground and aerial meta-data for localization and reconstruction are reviewed.
Localization and reconstruction are two highly related research areas. Both of them have developed rapidly in recent years. Apparently, with the help of ground and aerial meta-data integration, the performance of both localization and ...
- rapid-communicationJuly 2019
An efficient initial guess for the ICP method
Pattern Recognition Letters (PTRL), Volume 125, Issue CPages 721–726https://doi.org/10.1016/j.patrec.2019.07.019Highlights- A pseudo closed form solution is found with linear time.
- A statistic-based ...
The iterative closest point (ICP) method is a widely accepted solution for the point-based surface match problem, various improved visions are proposed based on this method. Although various improved visions are proposed, the ...
- rapid-communicationJuly 2019
Error-tolerant geometric graph similarity and matching
Pattern Recognition Letters (PTRL), Volume 125, Issue CPages 625–631https://doi.org/10.1016/j.patrec.2019.06.025Highlights- An intuitive approach to graph similarity and matching using geometric graphs.
- ...
Geometric graph matching is the process of evaluating the similarity between geometric graphs, where each vertex has an associated coordinate point in a plane. Exact matching computes a strict correspondence between two geometric ...
- rapid-communicationJuly 2019
Efficient large-scale geometric verification for structure from motion
Pattern Recognition Letters (PTRL), Volume 125, Issue CPages 166–173https://doi.org/10.1016/j.patrec.2018.09.028Highlights- GPU-based fundamental matrix estimation algorithm.
- GPU-based homography matrix estimation algorithm.
- GPU-based fast optimization algorithm.
Geometric verification is a fundamental problem in epipolar geometry, which estimates fundamental matrix and homography matrix to confirm that image pairs share a common 3D structure. However, it still suffers from low efficiency when it ...
- rapid-communicationJune 2019
Shape-aware label fusion for multi-atlas frameworks
Pattern Recognition Letters (PTRL), Volume 124, Issue CPages 109–117https://doi.org/10.1016/j.patrec.2018.07.008Highlights- An explicit shape model is incorporated into the multi-atlas segmentation framework.
Despite of having no explicit shape model, multi-atlas approaches to image segmentation have proved to be a top-performer for several diverse datasets and imaging modalities. In this paper, we show how one can directly incorporate ...
- research-articleJanuary 2017
Object recognition under severe occlusions with a hidden Markov model approach
The main contributions of this paper are: A new method for recognition of non-deformable severe occluded objects.Local shape descriptor from the wavelet coefficients of the tangent angle signature.Most likely object retrieval based on an ensemble of ...