An Adaptive Structural Learning of Deep Belief Network for Image-based Crack Detection in Concrete Structures Using SDNET2018

TL;DR

This paper introduces an adaptive deep belief network that self-organizes its structure during training, achieving high accuracy in crack detection on concrete images from the SDNET2018 dataset.

Contribution

The paper presents a novel adaptive DBN with self-organizing layers and neurons, specifically designed for image-based crack detection in concrete structures.

Findings

Achieved over 99.7% classification accuracy on SDNET2018 data

Demonstrated the adaptive DBN's ability to optimize network structure during learning

Identified issues with dataset annotation quality affecting results

Abstract

We have developed an adaptive structural Deep Belief Network (Adaptive DBN) that finds an optimal network structure in a self-organizing manner during learning. The Adaptive DBN is the hierarchical architecture where each layer employs Adaptive Restricted Boltzmann Machine (Adaptive RBM). The Adaptive RBM can find the appropriate number of hidden neurons during learning. The proposed method was applied to a concrete image benchmark data set SDNET2018 for crack detection. The dataset contains about 56,000 crack images for three types of concrete structures: bridge decks, walls, and paved roads. The fine-tuning method of the Adaptive DBN can show 99.7%, 99.7%, and 99.4% classification accuracy for three types of structures. However, we found the database included some wrong annotated data which cannot be judged from images by human experts. This paper discusses consideration that purses the major factor for the wrong cases and the removal of the adversarial examples from the dataset.