Training a Convolutional Neural Network to recognize metals surface defects using Keras (TensorFlow backend) with colab.
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.
The Simpsons characters recognition and detection using Keras (Part 1)