论文阅读笔记《Segmentation-based deep-learning approach for surface-defect detection》 技术标签:论文阅读笔记# 缺陷检测深度学习缺陷检测分割网络 核心思想 本文提出一种基于分割的表面缺陷检测算法,作者通过对网络结构的精心设计,能够仅利用30张带有标签的缺陷样本实现对网络的有效训练,实
所需训练样本个数 如上图所示,paper提出的网络,在仅有33个缺陷样本的训练下,AP能够达到99.9%;在仅有5个缺陷样本的训练下,AP依旧能够达到96.1%。超过了其它分割网络和商业软件在同等配置下的效果,一定程度上解决了深度学习所需样本数量大的问题。 所需训练时间 如上图所示: paper提出的网络在对单张图片进行检测的...
Surface-defect detectionVisual inspectionQuality controlDeep learningComputer visionSegmentation networksIndustry 4.0Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual ...
论文阅读- Segmentation-Based Deep-Learning Approach for Surface-Defect Detection,程序员大本营,技术文章内容聚合第一站。
(秒杀 DeepLabV3+ 和Unet 的缺陷检测网络) A Tensorflow implementation of "Segmentation-Based Deep-Learning Approach for Surface-Defect Detection" - sunchuanxi/Deep-Learning-Approach-for-Surface-Defect-Detection
To overcome this challenge, this work presents a rapid segmentation-based technique for surface defect detection. The proposed model is based on a modified U-Net, which introduces a hybrid residual module (SAFM), combining an improved spatial attention mechanism and a feedforward neural network in...
一种基于图像融合分割的实木地板表面缺陷检测方法,涉及地板表面缺陷检测领域,本发明针对区域生长算法存在的分割速度慢,分割不准确的问题,致使实木地板的表面缺陷检测速度慢,精度低的问题,影响其质量与分选等级. Image fusion segmentation based on the wood floor surface defect detection method for detecting surface ...
Surface Defect Detection of Button Cells Based on the Fusion of Object Detection and Semantic Segmentationdoi:10.1007/s13369-024-09902-wThere are variety of defects on the surface of button cells with complex morphology and cross-scale features, which leads to the problems of low accuracy and ...
Model-based SegmentationLaser brazing weldsLaser visionThis paper proposes a defect detection method using laser vision with model-based segmentation for laser brazing welds on car body surface, in which a dynamic ideal surface (DIS), composed of a series of dynamic ideal contours (DIC), is ...
Figure 4. Overview of the defect detection method applied to a real production line. DOG: Difference of Gaussian, MGRTS: mask gradient response-based threshold segmentation, ROI: region of interest. 2.1. ROI Extraction In the region of interest (ROI) extraction stage, in order to ensure the ...