作者: Fátima NS Medeiros , Geraldo LB Ramalho , Mariana P Bento , Luiz CL Medeiros , None
DOI: 10.1155/2010/817473
关键词:
摘要: We present a methodology for automatic corrosion detection in digital images of carbon steel storage tanks and pipelines from petroleum refinery. The database consists optical taken equipments exposed to marine atmosphere during their operational life. This new approach focuses on color texture descriptors accomplish corroded noncorroded surface area discrimination. performance the proposed is evaluated by using Fisher linear discriminant analysis (FLDA). presents two main advantages: No refinery stoppages are required potential-related catastrophes can be prevented.