Rethinking Rotation-Invariant Recognition of Fine-Grained Shapes From the Perspective of Contour Points.

Journal: IEEE transactions on pattern analysis and machine intelligence
Published Date: Mar 1, 2026

Abstract

Rotation-invariant recognition of shapes is a common challenge in computer vision. Recent approaches have significantly improved the accuracy of rotation-invariant recognition by encoding the rotational invariance of shapes as hand-crafted image features and introducing deep neural networks. However, the methods based on pixels have too much redundant information, and the critical geometric information is prone to early leakage, resulting in weak rotation-invariant recognition of fine-grained shapes. In this paper, we reconsider the shape recognition problem from the perspective of contour points rather than pixels. We propose an anti-noise rotation-invariant convolution module based on contour geometric aware for fine-grained shape recognition. The module divides the shape contour into multiple local geometric regions (LGA), where we implement finer-grained rotation-invariant coding in terms of point topological relations. We provide a deep network composed of five such cascaded modules for classification and retrieval experiments. The results show that our method exhibits excellent performance in rotation-invariant recognition of fine-grained shapes. In addition, we demonstrate that our method is robust to contour noise and the rotation centers.

Authors

  • Yanjie Xu
    Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China;State Key Laboratory of Tribology in Advanced Equipment, Tsinghua University, Beijing 100084, China;Beijing Key Lab of Precision/Ultra-Precision Manufacturing Equipments and Control, Tsinghua University, Beijing 100084, China.
  • Yunzhi Chen
    School of Information Engineering, Hangzhou Vocational & Technical College, Hangzhou, China.
  • Handing Xu
    Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China.
  • Tianmu Wang
    Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China.
  • Yaguan Li
  • Zhenguo Nie
    Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China. [email protected].

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals