用Gabor滤波与混合模型提升纹理缺陷检测精度
Surface Defect Detection with Gabor Filter Using Reconstruction-Based Blurring U-Net-ViT
- 融合U-Net局部特征与ViT全局感知，构建混合架构
- 在MVTec-AD等数据集上平均AUC达0.939，显著抗噪
- 通过后处理Gabor滤波增强缺陷方向与频率特征
本文提出一种基于Gabor滤波与重构式模糊U-Net-ViT的新型纹理表面缺陷检测方法。通过结合U-Net的局部特征提取能力与视觉变压器(ViT)的全局建模能力，模型可有效识别多种纹理中的缺陷。采用高斯滤波损失函数抑制背景噪声并突出缺陷模式，训练中引入盐与胡椒(SP)掩码以强化纹理-缺陷边界，在噪声环境下保持鲁棒性。后处理阶段应用Gabor滤波器，突出缺陷的方向性与频率特性。通过对滤波器尺寸、sigma、波长、gamma及方向等参数优化，该方法在MVTec-AD、Surface Crack Detection和Marble Surface Anomaly Dataset三个数据集上实现平均AUC 0.939。消融实验表明，最优滤波器尺寸与噪声概率对检测性能提升关键。
原文摘要 · Abstract (English)
This paper proposes a novel approach to enhance the accuracy and reliability of texture-based surface defect detection using Gabor filters and a blurring U-Net-ViT model. By combining the local feature training of U-Net with the global processing of the Vision Transformer(ViT), the model effectively detects defects across various textures. A Gaussian filter-based loss function removes background noise and highlights defect patterns, while Salt-and-Pepper(SP) masking in the training process reinforces texture-defect boundaries, ensuring robust performance in noisy environments. Gabor filters are applied in post-processing to emphasize defect orientation and frequency characteristics. Parameter optimization, including filter size, sigma, wavelength, gamma, and orientation, maximizes performance across datasets like MVTec-AD, Surface Crack Detection, and Marble Surface Anomaly Dataset, achieving an average Area Under the Curve(AUC) of 0.939. The ablation studies validate that the optimal filter size and noise probability significantly enhance defect detection performance.
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。