缺陷检测算法汇总(传统+深度学习方式)|综述、源码
共 2162字,需浏览 5分钟
·
2021-05-08 13:08
转载自 | 3D视觉工坊
作者 | Tom Hardy
链接 | https://zhuanlan.zhihu.com/p/362330594
文章是对缺陷算法的综述、源码等资源的汇总。
文献资料汇总:
https://github.com/Eatzhy/surface-defect-detection
综述:机器视觉表面缺陷检测综述
缺陷检测工具箱:
https://github.com/abin24/Saliency-detection-toolbox
基于深度学习方式
1、语义分割方式
https://github.com/Wslsdx/Deep-Learning-Approach-for-Surface-Defect-Detection
https://github.com/LeeWise9/Segmentation-Based-Surface-Defect-Detection
https://github.com/CristinaMa0917/Defects_Detection_MaskRCNN
2、目标检测方式
https://github.com/YeahHuang/Al_surface_defect_detection
3、基于GAN
https://github.com/hukefei/GAN-defect
4、不同行业应用
1)PCB
https://github.com/Ixiaohuihuihui/Tiny-Defect-Detection-for-PCB
https://github.com/chinthysl/AXI_PCB_defect_detection
https://github.com/gustavo95/pcb-defect-detection
2)钢材缺陷检测
https://github.com/khornlund/severstal-steel-defect-detection
https://github.com/Diyago/Severstal-Steel-Defect-Detection
https://github.com/toandaominh1997/Steel-Defect-Detection
https://github.com/rook0falcon/steel-defect-detection
3)胶囊缺陷检测
https://github.com/TSjianjiao/Defect-Detection-with-tensorflow
4)电池缺陷检测
https://github.com/cdeldon/thermography
https://github.com/evip/ButtonDefectDetection
5)织物缺陷检测
https://github.com/weningerleon/TextileDefectDetection
https://github.com/freedom-kevin/defect_detection
https://github.com/Johncheng1/Fabric-defect-detection
https://github.com/luissen/SSDT-A-single-shot-detector-for-PCB--defects
https://github.com/wangerniuniu/FabricDefectDetection
https://github.com/mynameiswangshiyi/AE-BP-fabric-defect-detection
6)水果和蔬菜缺陷检测
https://github.com/shyamsuresh14/Detection-of-defects-in-fruits-and-vegetables
其它
https://github.com/skokec/segdec-net-jim2019
https://github.com/zwb204/Industrial_defect_detection
https://github.com/wuziheng/SiliconWaferDefectDetection
https://github.com/qiucongying/Mcue
https://github.com/yjphhw/SACNN
缺陷检测数据集
https://github.com/abin24/Surface-Inspection-defect-detection-dataset
https://github.com/Eatzhy/Surface-defect-Detection-dataset
双一流高校研究生团队创建 ↓
专注于计算机视觉原创并分享相关知识 ☞
整理不易,点赞三连!