Nur Nafi’iyah, - and Chastine Fatichah, - and Darlis Herumurti, - and Eha Renwi Astuti, - (2020) The Use of Pre and Post Processing to Enhance Mandible Segmentation using Active Contours on Dental Panoramic Radiography Images. IEEE, 20 (2).

	Text (NASKAH) Artikel 18. The Use of Pre and Post Processing to Enhance Mandible Segmentation using Active Contours on.pdf Download (1MB)
	Text (TURNITIN) 46. 9% The Use of Pre and Post Processing to Enhance Mandible Segmentation using Active Contours on Dental Panoramic Radiography Images.pdf Download (2MB)
	Text (VALIDASI) 46. The Use of Pre and Post Processing to Enhance Mandible Segmentation using Active Contours on Dental Panoramic Radiography Images.pdf Download (211kB)
	Text (KARIL) 40. The Use of Pre and Post Processing to Enhance.pdf Download (112kB)

Abstract

Mandibular segmentation is indispensable to support the automation of the gender detection system based on the dental panoramic radiography image. However, the dental panoramic radiography image has low image contrast, the gray intensity value inhomogeneous, and the gray intensity value between the teeth and mandibular bone is almost indistinguishable. So, a good segmentation method is required to separate the mandible and teeth properly. This study aims to analyze the effect of the use of preprocessing and post-processing to enhance mandible segmentation on dental panoramic radiography images properly. In the preprocessing, we use contrast enhancement and Gaussian filters to make the mandibular area more prominent. Meanwhile, in the post-processing, we use erosion and opening morphology to remove the tooth area attached to the mandible. The mandibular segmentation uses the Active Contours method with predefined contour initialization. The dataset used is 86 dental panoramic radiographic images and the segmentation evaluation method uses Jaccard similarity. The experimental results show that the mandibular segmentation with preprocessing and postprocessing obtain Jaccard similarity values are 0.31 and 0.34, on average. Meanwhile, the results of mandibular segmentation with post-processing achieve the Jaccard similarity values are 0.51 and 0.52, on average.

Actions (login required)

View Item