Box-and-Ellipse-Based ANFIS for Bridge Coating Assessment

Abstract

In the late 1990s, image processing was first applied to steel bridge coating assessment in the United States. Yet, there has not been any robust method that could solve nonuniform illumination problems to date. In this regard, this paper aims to develop an approach that handles nonuniform illumination in rust image recognition. The proposed approach also contributes to rust intensity recognition and process automation. This paper adopts the a∗b∗ color configuration (of the L∗a∗b∗ color space) which is shown to be the best coordinate system for rust recognition by the proposed method. Different rust colors are regarded as relating to different degrees of rust intensity. Due to the difficulty of defining light rust colors, the adaptive-network-based fuzzy inference system (ANFIS) is used as the framework for the box-and-ellipse-based ANFIS (BE-ANFIS). Illumination adjustment is used to overcome the nonuniform illumination problem. The proposed BE-ANFIS is trained using 120 rust images of the size of 256×256 pixels. The performance of BE-ANFIS is compared to the fuzzy C-means (FCM) method, one of the most popular image recognition methods, and the adaptive ellipse approach (AEA) which is the writers’ previous approach. Based on testing 35 rust images, the results show that BE-ANFIS can better recognize rust intensity (i.e., distinguishing light and dark rusts) than FCM and AEA.