.png){kind=icon}
返回
A Lie algebra representation for efficient 2D shape classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.109078.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Riemannian manifold plays a vital role as a powerful mathematical tool in computer vision, with impor-tant applications in curved shape analysis and classification. Significant progress has recently been made by Riemannian framework based methods that achieved state-of-the-art classification accuracy and ro-bustness. However, these Riemannian manifold and Lie group methods require a very high computational complexity and do not include a description of the shape regions. This paper presents a novel mathemat-ical tool, called Block Diagonal Symmetric Positive Definite Matrix Lie Algebra (BDSPDMLA) to represent curves, which extends the existing Lie group representations to a compact yet informative Lie algebra representation. The proposed Lie algebra based method addresses the computational bottleneck problem of the Riemannian framework based methods. In addition, it allows the natural fusion of various regions information with curved shape features for a more discriminative shape description. Here the region in-formation is represented by values of distance maps, local binary patterns (LBP) and image intensity. Extensive experiments on five publicly available databases demonstrate that the proposed Lie algebra based method can achieve a speed of over ten thousand times faster than the Riemannian manifold and Lie group based baseline methods, while obtaining comparable accuracies for 2D shape classification.(c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Lie algebra
2D Shape classification
Covariance matrix
Lie group of SPD matrix
期刊
IF:
7.6
论文数:
1.4W
被引数:
4.5W
机构
引用论文
Exploiting Vibrational Strong Coupling to Make an Optical Parametric Oscillator Out of a Raman Laser
OAAI
.png){kind=icon}
OAAI分享收藏
查看更多内容