This paper presents an efficient algorithm to distinguish airvoids of polished concrete specimens using image processing for a fully automated image analysis system. In order to distinguish air-voids from aggregates and cement paste, the proposed algorithm adopts mathematical morphology and color image processing. First, air-voids and aggregates are extracted, based on a global threshold which is selected from histogram processing so that the proposed algorithm can cope with the variation of illumination; then, color and noise information discriminate between aggregates and air-voids. Experimental results show that the proposed algorithm can be applied to a fully automated image analysis system.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.