Abstract
<p><em style="text-align: justify; text-indent: 14.2pt;"><span style="font-family: 'Times New Roman',serif; mso-ansi-language: EN;" lang="EN">In pattern recognition, image processing plays a role in automatically separating objects from the background. In addition, the object will be processed by the pattern classifier. In the medical world, image processing plays a very important role. CT Scan (Computed Tomography) or CAT Scan (Computed Axial Tomography) is an example of an image processing application that can be used to view fragments or cross sections of parts of the human body. Tomography is the process of producing two-dimensional images from three-dimensional film through several one-dimensional scans. Magnetic resonance imaging (MRI) is the image most often used in the field of radiology. MRI images can display the anatomical details of objects clearly in multiple sections (multiplanar) without changing the patient's position. In this study, two methods were compared, namely K-Means and Fuzzy C Means, in a segmentation process with the aim of separating between normal areas or areas with disturbances (lesions). The images used are brain and chest MRI images with a total of 10 MRI images. The image quality of the segmentation results is compared with the quality test using the Variation of Information (VOI) parameters, Global Consistency Error (GCE), MSE (Mean Square Error), PSNR (Peak Signal to Noise Ratio) and segmentation time.</span></em></p><pre style="text-align: justify; text-indent: 14.2pt;"><em><span style="font-family: 'Times New Roman',serif; mso-ansi-language: EN;" lang="EN">In pattern recognition, image processing plays a role in automatically separating objects from the background. In addition, the object will be processed by the pattern classifier. In the medical world, image processing plays a very important role. CT Scan (Computed Tomography) or CAT Scan (Computed Axial Tomography) is an example of an image processing application that can be used to view fragments or cross sections of parts of the human body. Tomography is the process of producing two-dimensional images from three-dimensional film through several one-dimensional scans. Magnetic resonance imaging (MRI) is the image most often used in the field of radiology. MRI images can display the anatomical details of objects clearly in multiple sections (multiplanar) without changing the patient's position. In this study, two methods were compared, namely K-Means and Fuzzy C Means, in a segmentation process with the aim of separating between normal areas or areas with disturbances (lesions). The images used are brain and chest MRI images with a total of 10 MRI images. The image quality of the segmentation results is compared with the quality test using the Variation of Information (VOI) parameters, Global Consistency Error (GCE), MSE (Mean Square Error), PSNR (Peak Signal to Noise Ratio) and segmentation time.</span></em></pre>
Highlights
ABSTRAK Dalam pengenalan pola, pemrosesan gambar berperan dalam memisahkan objek secara otomatis dari latar belakang
image processing plays a role in automatically separating objects from the background
the object will be processed by the pattern classifier
Summary
Pemrosesan citra adalah bagian penting dari fondasi berbagai aplikasi praktis, seperti pengenalan pola, penginderaan jauh melalui satelit atau pesawat, dan penglihatan mesin. Ada kebutuhan untuk meningkatkan kualitas gambar MRI medis dengan tujuan menghasilkan gambar dengan kualitas yang jauh lebih tinggi daripada gambar aslinya. TEORI Segmentasi citra menggunakan algoritma K-Means, termasuk penelitian oleh Nurhasanah [1] yang mengusulkan pemetaan putih, abu-abu, dan CSF dalam segmen citra MRI menggunakan teknik clustering KMeans. Penelitian selanjutnya oleh Jipkate dan Gohokar [2] membandingkan algoritma segmentasi citra K-Means dengan fuzzy clustering c-Means. Studi lain [3] yang dilakukan oleh Samma dan Salam menyarankan segmentasi citra berdasarkan algoritma clustering K-Means adaptif. Kami menggunakan K-Means Pooling dan Threshold Processing untuk membandingkan hasil segmentasi. Anda dapat menggunakan parameter seperti MSE, PSNR, dan SNR untuk lebih membagi lagi performa gambar yang berbeda. Dan piksel di sudut kanan bawah memiliki koordinat (N-1, M-1)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
