Fuzzy genetic-based noise removal filter for digital panoramic X-ray images

Publication date: Available online 5 September 2018Source: Biocybernetics and Biomedical EngineeringAuthor(s): Mehravar Rafati, Fateme Farnia, Mahdi Erfanian Taghvaei, Ali Mohammad NickfarjamAbstractThis paper proposed a novel fuzzy genetic-based noise removal filter and surveyed the gain of popular filters for noise removal in the digital orthopantomography (OPG) images. The proposed filter is a non-invasive technique for attaining sub-clinical information from the areas of interest in each tooth, both jaws and maxillofacial.The proposed Poisson removal filter combines 4th-order partial differential equations (PDE), total variation (TV) and Bayes shrink threshold accompanied by fuzzy genetic algorithm (FGA) and the exact unbiased inverse of generalized Anscombe transformation (EUIGAT). Experiments were performed in order to show the effect of noise removal filters on 110 simulated, 106 phantom and 104 panoramic radiographic images for subjects (aged 30–60 years old, 50 males and 54 females). Various noises degraded filters and Canny edge detection was performed separately in three kinds of images. The program measured mean square error (MSE), peak signal to noise ratio (PSNR), image quality index (IQI), structural similarity index metric (SSIM) and figure of merit (FOM).The results verify that the proposed filter enhances physicians’ and dentists’ skill of diagnosing normal and pathological events in the teeth, jaws, temporomandibular joint (TMJ) regions and changeable...
Source: Biocybernetics and Biomedical Engineering - Category: Biomedical Engineering Source Type: research