Voids identification in rubberized mortar digital images using K-Means and Watershed algorithms

摘要: Abstract In the construction industry, use of sustainable raw materials has become a challenge. Rubber scrap tires have been investigated by several researchers as an alternative aggregate to conventional because it major environmental problem in all parts world. Scanning Electron Microscopy (SEM) images are contributing understanding influence this type main physical and mechanical properties cementitious composites. Voids derived from rubber mortar can be found SEM technique; however, that depends on visual analysis, having low accuracy recognition. To do so, image processing techniques used fill gap increasing reliability microstructural analysis. work, tire waste is 0%, 5%, 10%, 15% 30%, replacing, mass, aggregate. Density, voids index, water absorption resistance rubberized mortars were evaluated. Microscopic collected scanning electron microscopy subsequently applied technique for quantitative identification each mixture with rubber. Rubberized showed lower strength compared sample. However, due increase matrix rubber, property could calculated analysis aid technique, K-Means algorithm Watershed, which 88% relation The best characterization pathologies important tool fight against strength, aggregate, reduces extraction natural inadequate disposition tires.