Small Defect Detection Using Convolutional Neural Network Features and Random Forests

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review


We address the problem of identifying small abnormalities in an imaged region, important in applications such as industrial inspection. The goal is to label the pixels corresponding to a defect with a minimum of false positives. A common approach is to run a sliding-window classifier over the image. Recent Fully Convolutional Networks (FCNs), such as U-Net, can be trained to identify pixels corresponding to abnormalities given a suitable training set. However in many application domains it is hard to collect large numbers of defect examples (by their nature they are rare). Although U-Net can work in this scenario, we show that better results can be obtained by replacing the final softmax layer of the network with a Random Forest (RF) using features sampled from the earlier network layers. We also demonstrate that rather than just thresholding the resulting probability image to identify defects it is better to compute Maximally Stable Extremal Regions (MSERs). We apply the approach to the challenging problem of identifying defects in radiographs of aerospace welds.
Original languageEnglish
Title of host publicationEuropean Conference on Computer Vision
Place of PublicationSwitzerland
PublisherSpringer Nature
Number of pages15
ISBN (Electronic)9783030110185
ISBN (Print)9783030110178
Publication statusPublished - 2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Nature


  • Defect detection
  • Non-destructive evaluation
  • CNN
  • Local features
  • Random forests


Dive into the research topics of 'Small Defect Detection Using Convolutional Neural Network Features and Random Forests'. Together they form a unique fingerprint.

Cite this