从轮廓点出发，提升细粒度形状的旋转不变识别能力
Rethinking Rotation-Invariant Recognition of Fine-grained Shapes from the Perspective of Contour Points
- 基于轮廓点的几何感知模块，通过局部区域编码实现旋转不变性
- 在多个数据集上显著优于现有方法，噪声与旋转中心变化下仍稳定
- 适合需要高鲁棒性的细粒度视觉识别任务
旋转不变形状识别是计算机视觉中的常见挑战。现有方法通过手工特征编码旋转不变性并引入深度神经网络，显著提升了识别精度。然而，基于像素的方法冗余信息过多，关键几何信息易过早泄露，导致细粒度形状的旋转不变识别能力较弱。本文从轮廓点角度重新审视形状识别问题，提出一种抗噪的旋转不变卷积模块（ANRICN_CGA），将形状轮廓划分为多个局部几何区域（LGA），基于点的拓扑关系实现更细粒度的旋转不变编码。构建由五个级联模块组成的深度网络，用于分类与检索实验。结果表明，该方法在细粒度形状的旋转不变识别中表现优异，且对轮廓噪声和旋转中心变化具有强鲁棒性。代码已开源：https://github.com/zhenguonie/ANRICN_CGA。
原文摘要 · Abstract (English)
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. The source code is available at https://github.com/zhenguonie/ANRICN_CGA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。