Fully adaptive segmentation of cracks on concrete surfaces. (May 2020)

• Record Type: Journal Article
• Authors: Nnolim, Uche A.
• Is Part Of: Computers & electrical engineering. Volume 83(2020)
• Publication Date: 2020-05
• Subjects: Adaptive partial differential equations -- Anisotropic forward backward diffusion -- Fuzzy homomorphic total variation regularization -- statistical area discrimination -- Nonlinear statistical dispersion edge filters -- Embedded software development; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2020.106561
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Forward and backward diffusion coupled fuzzy intensification-based partial differential equation (FAB-FINT PDE) to strengthen edges and smoothen background noise and features. Use of statistical dispersion filters for flexibility and to capture more detail during edge detection process. Stable, adaptive, gradient-optimized PDE-based fuzzy INT. Elimination of arbitrary dilation and thinning processes due to adaptive statistical area discrimination process. Fully adaptive scheme except for anisotropic diffusion (AD) and forward-backward diffusion Laplacian (FAB-LAP) iterations and area thresholding operations. Abstract: In this study, we present fully automated image processing algorithms for detection of cracks on concrete surfaces. The acquired images of these concrete surfaces are the inputs to the proposed system. Solutions are developed for factors, which hinder accurate automated crack region analysis. These factors include noise, rough textures, uneven illumination and poor contrast. Both subjective and objective evaluation using standard datasets indicate better performance than several algorithms from the literature. Furthermore, the proposed scheme is implemented and deployed as a Java software application. Graphical abstract: Image, graphical abstract