Classification of Rust Grades on Steel Surfaces
نویسندگان
چکیده
Selecting most representative features among a huge feature set is considered in this paper. One feature extraction and five feature selection algorithms are tested on features obtained form steel surfaces. Two new feature selection algorithms are introduced in this paper. Performance measure for feature selection algorithms is also introduced as a new method to select the best performing feature selection algorithm. Steel surfaces are classified as rusty and clean according to selected features by each selection algorithm.
منابع مشابه
Automated Inspection of Steel Structures
In this paper, the problem of automatic classification of rust grades on steel surfaces is considered. Three texture analysis methods are studied to form features from steel surfaces. Nearest Neighbor classifier is used for classification of steel surface types. The results indicate that automation of the inspection and classification process is feasible.
متن کاملAutomated Defect Recognition Method by Using Digital Image Processing
As existing infrastructure systems are aged and deteriorated rapidly, state agencies started searching for more advanced ways to maintain their valuable assets to the acceptable level. One of them is the application of digital image processing. Recently, in the civil engineering domain, digital image processing methods have been developed to the areas of pavement conditions, underground pipelin...
متن کاملRust Formation Mechanism on Low Alloy Steels after Exposure Test in High Cl− and High SOx Environment
Exposure tests were performed on low alloy steels in high Cl- and high SOx environment, and the structure of the rust were analyzed by TEM (Transmission Electron Microscopy) and Raman Spectroscopy. In the exposure test site, the concentrations of Cl- and SOx were found to be high, which caused the corrosion of the steels. The conventional weathering steel (SMA: 0.6% Cr-0.4% Cu-Fe) showed higher...
متن کاملCharacterization of Rust Layers on Weathering Steels Air-Exposed for a Long Period
Several weathering steels and a plain carbon steel exposed to atmosphere for 17 years at Yokkaichi (at a coastal and industrial region) and Mikuni Pass (at a rural region) in Japan were analyzed and compared to find effects of environments on the formed rusts. Specimens were examined with electron probe microanalysis (EPMA), X-ray diffraction (XRD) and transmission electron microscope (TEM). Th...
متن کاملAutomated Rust Defect Recognition Method Based on Color and Texture Feature
Digital image processing has been applied to diverse industry disciplines. The wide application of digital image processing can be attributed to the following advantages: accuracy, objectivity, fastness, consistency, and the mixture of them. Although the RUst Defect Assessment(RUDA) method [1] was efficiently used to differentiate defective images from non-defective images on blue color coat, i...
متن کامل