Skip to content

Latest commit

 

History

History
13 lines (7 loc) · 644 Bytes

File metadata and controls

13 lines (7 loc) · 644 Bytes

A_surface_defect_detection_based_on_positive_samples

Generate randomly defects on positive samples and restore them with GAN.

Note:

  1. It is built from the Pix2Pix respository.

  2. There are three different models, consisting of autoencoder, segment model(Unet), and GAN (Pix2Pix).

  3. It is inspire by the paper "A Surface Defect Detection Method Based on Positive Samples".

  4. We Got the 5th place in the preliminary contest of National campus machine vison application competition.