CorrQuant: Development of a Web Platform for Image-Based Corrosion Quantification

Martínez Ramos, Cynthia y Gaona Tiburcio, Citlalli y Maldonado Bandala, Erick y Nieves Mendoza, Demetrio y Landa Ruiz, Laura y Lara Banda, María del Refugio y Estupiñan López, Francisco Humberto y Baltazar Zamora, Miguel Ángel y Jáquez Muñoz, Jesús Manuel y Cabral Miramontes, José Ángel y Almeraya Calderón, Facundo (2026) CorrQuant: Development of a Web Platform for Image-Based Corrosion Quantification. Journal of imaging, 12 (8). pp. 1-28. ISSN 2313-433X

Vista previa

Texto
31562.pdf - Versión Publicada
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Download (6MB) | Vista previa

URL o página oficial: https://doi.org/10.3390/jimaging12080359

Resumen

Corrosion remains one of the principal causes of degradation in metallic structures across a wide range of industrial sectors. Although visual inspection is routinely employed for preliminary corrosion assessment, its effectiveness depends heavily on operator experience and subjective interpretation. This work introduces CorrQuant, a web-based computer vision platform designed to transform qualitative corrosion images into quantitative measurements of corrosion extent and morphology. The proposed methodology processes images acquired with conventional mobile devices and integrates geometric calibration using a reference coin, perspective correction, adaptive image enhancement through Contrast Limited Adaptive Histogram Equalization (CLAHE), multi-descriptor feature extraction, and consensus-based corrosion segmentation. The detected corrosion regions are subsequently quantified to determine corrosion area, surface coverage, spatial distribution, morphological descriptors, and corrosion intensity maps. The methodology was verified using an aluminum specimen with a known corrosion area of 143 mm2 under both controlled illumination and optical stress-test conditions. Under standard acquisition conditions, corrosion-area estimation accuracies exceeding 90% were achieved. Additional evaluations under red illumination, fisheye, blur, and kaleidoscope distortions demonstrated that the proposed framework is considerably more sensitive to degradation of local image information than to variations in illumination spectrum. These results demonstrate the robustness of the proposed multi-descriptor voting strategy while defining the operational limits of the platform under challenging image acquisition conditions.

Tipo de elemento:

Article

Palabras claves no controlados:

Cuantificación de la corrosión; Procesamiento digital de imágenes; Visión por computadora; Segmentación de imágenes

Materias:

Q Ciencia > QA Matemáticas, Ciencias computacionales

Divisiones:

Ingeniería Mecánica y Eléctrica > Doctorado en Ciencias de la Ingeniería Aeronáutica

Usuario depositante:

Dra Citlalli Gaona

Creadores:

Creador	Email	ORCID
Martínez Ramos, Cynthia	cintiamtzramos@gmail.com	NO ESPECIFICADO
Gaona Tiburcio, Citlalli	citlalli.gaonatbr@uanl.edu.mx	orcid.org/0000-0001-9072-3090
Maldonado Bandala, Erick	NO ESPECIFICADO	NO ESPECIFICADO
Nieves Mendoza, Demetrio	NO ESPECIFICADO	NO ESPECIFICADO
Landa Ruiz, Laura	NO ESPECIFICADO	NO ESPECIFICADO
Lara Banda, María del Refugio	NO ESPECIFICADO	NO ESPECIFICADO
Estupiñan López, Francisco Humberto	NO ESPECIFICADO	NO ESPECIFICADO
Baltazar Zamora, Miguel Ángel	NO ESPECIFICADO	NO ESPECIFICADO
Jáquez Muñoz, Jesús Manuel	NO ESPECIFICADO	NO ESPECIFICADO
Cabral Miramontes, José Ángel	NO ESPECIFICADO	orcid.org/0000-0003-1483-3081
Almeraya Calderón, Facundo	facundo.almerayacl@uanl.edu.mx	orcid.org/0000-0002-3014-2814