Iterated Region for Interactive Image Segmentation on Dental Panoramic Radiograph

Abstract

Image Segmentation is a process to separate between foreground and background. Segmentation process in low contrast image such as dental panoramic radiograph image is not easily determined. Image segmentation accuracy determines the success or failure of the final analysis process. The process of segmentation can occur ambiguity. This ambiguity is due to an ambiguous area if it is not selected as a region so it may have occurred cluster errors. To solve this ambiguity, we proposed a new region merging by iterated region merging process on dental panoramic radiograph image. The proposed method starts from the user marking and works iteratively to label the surrounding regions. In each iteration, the minimal gray-levels value is merged so the unknown regions significantly reduced. This experiment shows that the proposed method is effective with an average of ME and RAE of 0.04% and 0.06%.

Segmentasi Citra Tenun Menggunakan Metode Otsu Thresholding dengan Median Filter

“…Pendekatan yang diterapkan dari metode otsu yaitu melakukan analisis diskriminan dengan menentukan suatu variabel yang mampu membedakan dengan groundtruth (observasi ahli). Bentuk korelasi tersebut dengan melihat rasio perbandingan dari piksel background yang dikenali sebagai objek dan rasio perbandingan dari piksel objek yang dikenali sebagai background[14]. Perhitungan ME dapat dilihat pada persamaan 4 dibawah:|𝐵0∩𝐵𝑇|+|𝐹0∩𝐹𝑇| antara dua kelompok atau lebih yang terbentuk secara 𝑀𝐸 = diskriminan yang dilakukan mampu memaksimalkan pemisahan objek (foreground) dan latar belakang (background) [10].…”