A Segmentation Method for Asphalt Quality Analysis


CİVELEK Ö., ÖZTÜRK M., Kutuk T., Kutuk S.

26th IEEE Signal Processing and Communications Applications Conference (SIU), İzmir, Turkey, 2 - 05 May 2018 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/siu.2018.8404825
  • City: İzmir
  • Country: Turkey
  • Recep Tayyip Erdoğan University Affiliated: Yes

Abstract

Asphalt quality is directly related to the proportions of the elements contained in the composition. Manual measurement of this ratio is a time-consuming and laborious process. In this work, a segmentation method is proposed for the images obtained on the surfaces of cut-out asphalt samples to measure the ratio automatically. For this purpose, a system has been created to obtain images under controlled lighting conditions from asphalt samples. The images obtained here are subjected to various filters to remove gray level irregularities. Then they segmented using the gray level histogram processing. The results were compared with manually segmented images by the expert and the performance analysis was given. The results showed that the proposed method has a general classification accuracy of higher than 85%.