Skip to content
Keep an Eye on Defects Inspection.
C++ Python C CMake C# Shell
Branch: master
Clone or download
Latest commit 1c458b3 May 4, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
app update. Mar 23, 2018
build/vc14 update. Mar 23, 2018
data init. Jan 15, 2018
docs/imgs update. Sep 15, 2018
extra update. Mar 23, 2018
model update model for train&detection. Sep 15, 2018
._README.md Update README.md. Sep 15, 2018
.gitignore update README.md. May 14, 2018
LICENSE update README.md. Jan 18, 2018
README.md Update README.md May 4, 2019

README.md

DEye (Keep an Eye on Defects Inspection)


1. Abstract

Defect Eye is an open source software library based on tensorflow1.4, which focus on surface defect inspection. The application area cover the full range of yield applications within the manufacturing environment, including incoming process tool qualification, wafer qualification, glass surface qualification, reticle qualification, research and development, and tool, process and line monitoring. Patterned and unpatterned wafer defect inspection and qualification tools find particles and pattern defects on the front surface, back surface and edge of the wafer, allowing engineers to detect and monitor critical yield excursions. Also, It can be used for medical image inpsection, including Lung PET/CT,breast MRI, CT Colongraphy, Digital Chest X-ray images.

DEye

2. Usage

Compiled tensorflow-r1.4 GPU version using CMake,VisualStudio 2015, CUDA8.0, cudnn6.0.

How to use DEye

  • Install VisualStudio Community2015 Install NVIDIA CUDA 8.0

  • git clone https://github.com/sundyCoder/DEye

  • Download tensorflow.dll, place it under DEye/bin

  • Download tensorflow.lib and libprotobuf.lib, place theme under DEye/extra/tensorflow-r1.4/

  • Download inception_v3_2016_08_28_frozen.pb, place it under DEye/data

  • Open Visual Studio Solution "DEye.sln" which should be under DEye/build/vc14,Solution configurations option choose "Release", Soluton Platform option choose "x64".

  • Build and run the GUI project, you can do model training for your inspection cases.

3. Applications

3.1 IC Chips Defects Inspection

3.2 Highway Road Crack Damage Inpection

3.3 Fabric Defects Inpection

3.4 Cover Glass Inpection

3.5 Civil Infrastructure Defect Detection

3.6 Power lines Crack Detection

3.7 Medical Image Classification

4. Datasets

  1. Weakly Supervised Learning for Industrial Optical Inspection

    DAGM: https://hci.iwr.uni-heidelberg.de/node/3616

  2. Micro surface defect database

    https://pan.baidu.com/s/1QM0AxlGjUlkHHyxwamIMmA

  3. Oil pollution defect database

    https://pan.baidu.com/s/1_aU_Bfh7lcxpYW1no2MlUQ

  4. Bridge Crack Image Data

    http://pan.baidu.com/s/1bplPrPl

  5. ETHZ Datasets

    ETHZ: http://www.vision.ee.ethz.ch/en/datasets/

  6. RSDDs dataset

    http://icn.bjtu.edu.cn/Visint/resources/RSDDs.aspx

  7. Crack Forest Datasets

    https://github.com/cuilimeng/CrackForest

  8. CV Datasets on the Web

    http://www.cvpapers.com/datasets.html

  9. An RGB-D dataset and evaluation methodology for detection and 6D pose estimation of texture-less objects

    http://cmp.felk.cvut.cz/t-less/

  10. ** CV Dataset on the web **

    http://cvpapers.com/datasets.html

5. Contact

Notice: Any comments and suggetions are welcomed, kindly please introduce yourself(name, country, organization etc.) when contact with me, thanks for your cooperation.

6. TODO List

  • A user-friendly GUI ( welcome to contact with me if you want to be a collaborator)

7. License

Apache License 2.0

8. Citation

Use this bibtex to cite this repository:

@misc{DEye,
  title={CNN-based Manufacturing Defect Detection on Tensorflow},
  author={Sundy},
  year={2017},
  publisher={Github},
  journal={GitHub repository},
  howpublished={\url{https://github.com/sundyCoder/DEye}},
}
You can’t perform that action at this time.