Peningkatan Kualitas Citra CT-Scan dengan Penggabungan Metode Filter Gaussian dan Filter Median

Penulis

  • Sumijan Sumijan Sumijan Universitas Putra Indonesia YPTK Padang http://orcid.org/0000-0002-9932-4325
  • Ayu Widya Purnama Universitas Putra Indonesia "YPTK" Padang
  • Syafri Arlis Universitas Putra Indonesia”YPTK” Padang

DOI:

https://doi.org/10.25126/jtiik.201966870

Kata Kunci:

Median Filter & Gaussian Filter, Image CT-Scan, Noise speckle & Poisson

Abstrak

Perkembangan alat teknologi akuisisi citra medis, satu diantaranya adalah teknologi yang lazim disebut CT-scan. CT-Scan (Computed Tomography Scan) adalah prosedur untuk mendapatkan gambaran dari berbagai area kecil dari tulang termasuk tengkorak kepala dan otak. Citra hasil akuisisi atau rekaman CT-Scan dapat mebantu memperjelas adanya dugaan yang kuat tentang kelainan yang terjadi pada otak. Kualitas citra dapat dilakukan dengan proses mengubah citra menjadi citra baru sesuai kebutuhan, salah satu cara seperti fungsi transformasi, operasi matematis dan pemfilteran. Peningkatan kualitas citra CT-Scan diperlukan untuk objek keputusan medis yang mempunyai kualitas tidak baik, misalnya citra mengalami derau (noise), citra terlalu terang atau gelap, citra kurang tajam, dan kabur. Proses Peningkatan kualitas citra dapat dilakukan dengan menerapkan salah satu metode pemfilteran, untuk memperbaiki kualitas citra agar dihasilkan citra yang lebih baik dari citra aslinya. Metode gaussian filter untuk mengurangi noise speckle dan poisson pada citra otak pada CT-Scan. Pada citra noise gaussian, standar deviasi yang terbaik dalam mengurangi noise bernilai satu. Namun untuk citra noise speckle dan poisson nilai standar tidak dapat mengurangi noise tersebut. Hal ini dikarenakan standar deviasi adalah parameter dalam proses gaussian filter hanya dapat untuk noise Gaussian normal, untuk mengurangi noise sebaran tidak normal (non-linier) digunakan median filter. Kelemahan gaussian filter pada noise nilai parameter tidak stabil (non-linier) dapat diatasi pada filter median. Dari hasil penggabungan filter gaussian dan filter median filter dapat meningkatkan kualitas citra dan menguranggi noise lebih baik sebaran normal dan tidak normal.

Abstract

The development of medical image acquisition technology tools, one of which is the technology commonly called CT scan. CT-Scan (Computed Tomography Scan) is a procedure to get a picture of various small areas of bone including the skull and brain. Image acquisition results or CT-Scan recordings can help clarify the existence of strong suspicions about abnormalities that occur in the brain. Image quality can be done by the process of changing the image into a new image as needed, one way such as the transformation function, mathematical operations and filtering. Increasing the quality of CT-Scan images is needed for medical decision objects that have poor quality, for example images experience noise (noise), images are too bright or dark, images are less sharp, and blurred. The process of improving image quality can be done by applying one of the filtering methods, to improve image quality to produce a better image than the original image. Gaussian filter method to reduce speckle and poison noise in brain images on CT scan. In the Gaussian noise image, the best standard deviation in reducing noise is one. However, for speckle noise images and standard poison values it cannot reduce the noise. This is because the standard deviation is a parameter in the Gaussian filter process that can only be used for normal Gaussian noise, to reduce the abnormal noise distribution (non-linear) the median filter is used. The weakness of the Gaussian filter on the noise value of an unstable (non-linear) parameter can be overcome in the median filter. From the results of combining the Gaussian filter and median filter, it can improve image quality and reduce noise better than normal and abnormal distribution.

Downloads

Download data is not yet available.

Biografi Penulis

  • Sumijan Sumijan Sumijan, Universitas Putra Indonesia YPTK Padang
    Wakil Rektor I  Universitas Putra Indonesia YPTK Padang

Referensi

AFSHARI, H H, S A GADSDEN, and S HABIBI. 2017. Signal Processing Author ’S Accepted Manuscript Gaussian Filters for Parameter and State Recent Trends To Appear in : Signal Processing Gaussian Filters for Parameter and State Estimation : A General Review of Theory and Recent Trends. Elsevier. http://dx.doi.org/10.1016/j.sigpro.2017.01.001.

ARIPIN, SOEB, and HERY SUNANDAR. 2017. “Perancangan Aplikasi Perbaikan Citra Pada Hasil Screenshot Menggunakan Metode Interpolasi Linier 1.” (October).

CABELLO, FRANK. 2015. “W ; O _ Wll Rllllllllill â€TM Entil IIIII III.” : 28–33.

CHARALAMPIDIS, DIMITRIOS. 2016. “Recursive Implementation of the Gaussian Filter Using Truncated Cosine Functions.” IEEE Transactions on Signal Processing 64(14): 3554–65.

HUANG, YULONG, YONGGANG ZHANG, XIAOXU WANG, and LIN ZHAO. 2015. “Gaussian Filter for Nonlinear Systems with Correlated Noises at the Same Epoch.” Automatica 60: 122–26.

JULIANA, AJI, and AGUNG TRIAYUDI. 2014. “Implementasi Morphological Filtering Untuk Penajaman Citra Cctv.” Protekinfo 1(September): 2–6.

JULIO, R. OLIVEIRA, LEONARDO B. SOARES, E. A.C. COSTA, and SERGIO BAMPI. 2016. “Energy-Efficient Gaussian Filter for Image Processing Using Approximate Adder Circuits.” In Proceedings of the IEEE International Conference on Electronics, Circuits, and Systems, , 450–53.

LIU, CHANG, ZHAOWEI SHANG, and QIAOSONG CHEN. 2016. “An Adaptive Tone Mapping Algorithm Based on Gaussian Filter.” : 0–5.

NUGROHO, HENDRO. 2017. “Image Enhancement Pada Screen Capture CCTV Dengan Menggunakan Metode Histogram Ekualisasi.” 2(2): 99–106.

SEDDIK, HASSENE, SONDES TEBBINI, and EZZEDDINE BEN BRAIEK. 2014. “Intelligent Automation & Soft Computing Smart Real Time Adaptive Gaussian Filter Supervised Neural Network for Efficient Gray Scale and RGB Image De-Noising.” Intelligent Automation and Soft Computing 20(3): 347–64. http://dx.doi.org/10.1080/10798587.2014.888242.

SUGANESH, V, and J FLORENCE POOVATHY. 2016. “Filtering of Gaussian Filter Based Embedded Enhancement Technique for Compressively Sensed Images.” : 2177–81.

SUMIJAN, M. S., HARLAN, J., & WIBOWO, E. P. 2017. Hybrids Otsu method, Feature region and Mathematical Morphology for Calculating Volume Hemorrhage Brain on CT-Scan Image and 3D Reconstruction. Telkomnika, 15(1), 283-291.

SUMIJAN, S., YUHANDRI, Y., & BOY, W. (2016). Detection and Extraction of Brain Hemorrhage on the CT-Scan Image using Hybrid Thresholding Method. UPI YPTK Journal of Computer Science and Information Technology, 1(1).

SWAMINATHAN, R, PRIYA JHA, ASIF IQBAL, and MANOJ WADHWA. 2013. “Efficient Satellite Image Enhancement Technique Based On Filtering And Interpolation Methods.” 2(7): 1677–82.

Yano, Takahiro, and Yoshimitsu Kuroki. 2016. “Fast Implementation of Gaussian Filter by Parallel Processing of

SETIANINGSIH, CASI, SITI NURHAYATI, dan RIDWAN. 2011. “Medical Imaging”. Jurusan Teknik Elektro Institut Teknologi Telkom Bandung.

HAMA, SHOKHAN MAHMOUD dan MUZHIR SHABHAN AL-ANI. 2014. Medical Image Based on Efficient Approach for Adaptive Anisotropic Diffusion. International Journal of Advances in Engineering & Technology, ISSN : 22311963

WEERATUNGA, S. K. DANC. KAMATH. 2003. A Comparison of PDE based Non- Linear Anisotropic Diffusion Techniques for Image Denoising. Lawrence Livermore National Laboratory Technical Information Department’s Digital Library.

MALATHI, K dan R. NEDUNCHELIAN. 2014. “ Comparison of Various Noises and Filters for Fundus Images Using pre-Processing Techniques”. Bioinformatics, ISSN 0975-6299.

SUTOYO, T et al. 2009. Teori Pengolahan Citra Digital. Yogyakarta: Penerbit Andi.

OCEANDRA, M. HAKIKI. 2013. “Pengurangan Noise pada Citra Digital Menggunakan Metode Statistik mean, median, Kombinasi dan Rekursif Filter”. Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif kasim Riau Pekanbaru.

PRIMAYUNITA, FITRI , AGUS ZAINAL ARIFIN, dan ANNY YUNIARTI. “Implementasi Metode Klasifikasi Fuzzy C-Means Menggunakan Algoritma Multiscale Diffusion filtering”. Teknik Informatika, Fakultas Teknologi Informasi, Institut Teknologi Sepuluh Nopember.

HUMAIRA dan RASYIDAH. 2011. “Analisis Pengaruh Noise Terhadap Deteksi Wajah Manusia pada Citra Berwarna menggunakan Fuzzy”. Poli Rekayasa, Vol 6, No 2, ISSN 1858-3709.

GILBOA, GUY, NIR SOCHEN, dan YEHOSHUA Y. ZEEVI. 2002. Forward-and- Backward Diffusion Processes for Adaptive Image Enhancement and Denoising. IEEE Transactions on Image Processing, Vol 11, NO.7.

IRYANTO , F. FRISTELLA , dan P. H. GUNAWAN. 2016. Pendekatan Numerik pada Model Isotropic dan Anisotropic Diffusion untuk Mendeteksi Tepi pada Pengolahan Citra. Ind. Journal on Computing Vol 1, Issue. 2, ISSN 2460-9056.

SEBATUBUN, MARIA MEDIATRIX. 2016. Peningkatan Kualitas Citra X-Ray Paru- Paru Menggunakan Contrast Limited Adaptive Histogram Equalization dan gaussian filter. Seminar Riset Teknologi Informasi (SRITI).

WEICKERT, JOACHIM. 2001. Anisotropic Diffusion in Image Processing. Denmark : B. G. Teubner Stuttgart.

PERONA, PIETRO dan JITENDRA MALIK. 1990. Scale-Space and Edge Detection Using Anisotropic Diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol 12, NO. 7.

SMOLKA, BOGDAN. 2002. On The Application of The Forward and Backward Diffusion Scheme for Image Enhancement. Journal of Medical Informatics & Technologies vol.3, ISSN 1642-6037.

BOOMGAARD, REIN VAN DEN. TT. “Algorithms for Non-Linear Diffusion Matlab in a Literate Programming Style”. Netherlands : Intelligent Sensory Information Systems University of Amsterdam.

WIJANARTO. 2009. Restorasi Citra Digital dengan Algoritma Inpainting. Techno.Com, Vol 8, No.1.

Diterbitkan

02-12-2019

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Peningkatan Kualitas Citra CT-Scan dengan Penggabungan Metode Filter Gaussian dan Filter Median. (2019). Jurnal Teknologi Informasi Dan Ilmu Komputer, 6(6), 591-600. https://doi.org/10.25126/jtiik.201966870