Article
Ceramic Cracks Segmentation with Deep Learning
Gerivan Santos Junior * , Janderson Ferreira, Cristian Millán-Arias , Ramiro Daniel, Alberto Casado Junior
and Bruno J. T. Fernandes
Citation: Junior, G.S.; Ferreira, J.;
Millán-Arias, C.; Ruiz, D.; Junior,
A.C.; Fernandes, B.J.T. Ceramic
Cracks Segmentation with Deep
Learning. Appl. Sci. 2021, 11, 6017.
https://doi.org/10.3390/app11136017
Academic Editor: Antonio
Fernández-Caballero
Received: 7 May 2021
Accepted: 26 May 2021
Published: 28 June 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Polytechnic School of Pernambuco, University of Pernambuco, Recife 50720-001, Brazil; jrb@ecomp.poli.br (J.F.);
ccma@ecomp.poli.br (C.M.-A.); rdbr@poli.br (R.D.); acasado@poli.br (A.C.J.); bjtf@ecomp.poli.br (B.J.T.F.)
* Correspondence: gcsj@ecomp.poli.br
Abstract:
Cracks are pathologies whose appearance in ceramic tiles can cause various damages due
to the coating system losing water tightness and impermeability functions. Besides, the detachment
of a ceramic plate, exposing the building structure, can still reach people who move around the
building. Manual inspection is the most common method for addressing this problem. However, it
depends on the knowledge and experience of those who perform the analysis and demands a long
time and a high cost to map the entire area. This work focuses on automated optical inspection to find
faults in ceramic tiles performing the segmentation of cracks in ceramic images using deep learning
to segment these defects. We propose an architecture for segmenting cracks in facades with Deep
Learning that includes an image pre-processing step. We also propose the Ceramic Crack Database, a
set of images to segment defects in ceramic tiles. The proposed model can adequately identify the
crack even when it is close to or within the grout.
Keywords: deep learning; segmentation; ceramics; cracks; image
1. Introduction
In civil construction, buildings must be able to withstand the action of degradation
agents for a predetermined or predicted time [
1
]. The building’s facades include the
cladding system that serves to protect the building from external degradation agents,
in addition to providing functional and aesthetic comfort to its users [
2
]. Pathological
manifestations are common at these points, and they occur more frequently in ceramic
materials, which are used on a large scale in buildings. Besides, these manifestations arise
in other types of materials, such as mortar and stone. They can be related to several factors
such as excessive load, humidity variation, thermal variation, biological agents, material
incompatibility, and atmospheric agents [
3
]. These manifestations compromise the essential
function of protection, which aims to protect the coated surfaces against the agents that
cause deterioration that can present themselves in different ways. Thus, the consequences
can range from aesthetic problems or performance of coating to risks of accidents with
people, substantially aggravated by the height of the buildings [4].
The main types of pathological manifestations associated with ceramic facade cover-
ings are cracks, efflorescence, detachment, and those resulting from biological processes.
Among these, the fissure is the most found in the literature since it compromises the build-
ing safety, puts at risk the people that travel around it, and presents a more critical aesthetic
aspect [3,5–7].
A fissure’s main characteristic is the rupture appearance on the ceramic plate surface
or body, causing the loss of the facade’s integrity and uncovers some of its components,
the plates, or joints. When the fissure happens, a detachment of the substrate plate is
generated [4].
Image processing techniques (IPTs) are currently applied in civil engineering for
images collected from inspections. These techniques emerged to detect cracks in the civil
infrastructure, partially reducing the work done by human beings, and used several image
Appl. Sci. 2021, 11, 6017. https://doi.org/10.3390/app11136017 https://www.mdpi.com/journal/applsci
