用注意力和统计检验提升边缘检测精度，抗噪能力更强。
Edge Detection based on Channel Attention and Inter-region Independence Test
- 结合通道注意力与区域独立性检验，自适应增强边缘特征。
- 在BSDS500和NYUDv2上F-measure分别达0.635和0.460，优于现有方法。
- 适合高精度工业场景，对噪声敏感度低，结果更干净。
现有边缘检测方法常面临噪声放大和非显著细节过度保留的问题，限制了其在高精度工业场景中的应用。为此，我们提出CAM-EDIT框架，融合通道注意力机制（CAM）与基于独立性检验的边缘检测（EDIT）。CAM模块通过多通道融合自适应增强具有区分性的边缘特征，而EDIT模块则利用区域级统计独立性分析（采用Fisher精确检验和卡方检验）抑制无关噪声。在BSDS500和NYUDv2数据集上的大量实验表明，该方法达到领先性能：相比传统方法（如Canny、CannySR），F-measure分别提升19.2%至26.5%；优于最新学习型方法（TIP2020、MSCNGP）。噪声鲁棒性评估显示，在高斯噪声下，该方法比基线提升2.2% PSNR。定性结果显示边缘图更清晰，伪影更少，展现出在高精度工业应用中的潜力。
原文摘要 · Abstract (English)
Existing edge detection methods often suffer from noise amplification and excessive retention of non-salient details, limiting their applicability in high-precision industrial scenarios. To address these challenges, we propose CAM-EDIT, a novel framework that integrates Channel Attention Mechanism (CAM) and Edge Detection via Independence Testing (EDIT). The CAM module adaptively enhances discriminative edge features through multi-channel fusion, while the EDIT module employs region-wise statistical independence analysis (using Fisher's exact test and chi-square test) to suppress uncorrelated noise.Extensive experiments on BSDS500 and NYUDv2 datasets demonstrate state-of-the-art performance. Among the nine comparison algorithms, the F-measure scores of CAM-EDIT are 0.635 and 0.460, representing improvements of 19.2\% to 26.5\% over traditional methods (Canny, CannySR), and better than the latest learning based methods (TIP2020, MSCNGP). Noise robustness evaluations further reveal a 2.2\% PSNR improvement under Gaussian noise compared to baseline methods. Qualitative results exhibit cleaner edge maps with reduced artifacts, demonstrating its potential for high-precision industrial applications.
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。