📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

CTSegNet is an end-to-end 3D segmentation package for large X-ray tomographic datasets using 2D fully convolutional neural networks (fCNN).

The core code of AGCA: An Adaptive Graph Channel Attention Module for Steel Surface Defect Detection

The re-labeled NRSD-MN dataset, AMFF-YOLOX source code and paper "AMFF-YOLOX: Towards an Attention Mechanism and Multiple Feature Fusion Based on YOLOX for Industrial Defect Detection".

An application to create 2D geometry. A flexible user-friendly application to create 2D objects (points, curves and surfaces).

Detect featured surfaces of unstructured meshed.

缺陷检测文献记录

（最先进的缺陷检测网络） A Tensorflow implementation of "Segmentation-Based Deep-Learning Approach for Surface-Defect Detection"

This is an anomaly detection classification algorithm based on CNN based approach

C# implementation of random closed domain generator

Pytorch Implement of the paper "Segmentation-Based Deep-Learning Approach for Surface Defect Detection"

Salient Object Detection: A Benchmark

The App allows you to measure the distance between two points in space.

Exploiting surroundedness for saliency detection: a boolean map approach

导光板缺陷检测(a simple mura detect project)

基于DCN（Faster R-CNN,RFCN的钢铁检测实验）

Automated On-line Fast Detection for Surface Defect of Steel Strip Based on Multivariate Discriminant Function

My code for Tianchi competition(Al surface detect detection). My final rank is 10/2972.

基于PSPNet101的钢铁分割实验

Pytorch implementation of Real Time Image Saliency for Black Box Classifiers https://arxiv.org/abs/1705.07857