Skip to content

Training a CNN to recognize metals surface defects using Keras (TensorFlow backend) with colab.

Notifications You must be signed in to change notification settings

celine-hsieh/Metal_Training--CNN

Repository files navigation

Metal_Training-CNN

Training a Convolutional Neural Network to recognize metals surface defects using Keras (TensorFlow backend) with colab.

Database

NEU Surface Defect Database

Six kinds of typical surface defects of the hot-rolled steel strip are collected, i.e., rolled-in scale (RS), patches (Pa), crazing (Cr), pitted surface (PS), inclusion (In) and scratches (Sc). The database includes 1,800 grayscale images: 300(split into 240 images for training and 60 images for testing.) samples each of six different kinds of typical surface defects.

Result

image

References

SimpsonRecognition

The Simpsons characters recognition and detection using Keras (Part 1)

About

Training a CNN to recognize metals surface defects using Keras (TensorFlow backend) with colab.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published