Wibirama, Sunu
Komunitas Ilmuwan dan Profesional Muslim Indonesia

Published : 6 Documents

Found 6 Documents

Rekonstruksi dan Visualisasi Objek 3-D Berbasis Algoritma Direct Linear Transformation Wibirama, Sunu; Hidayat, Risanuri
Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI) Vol 1, No 2 (2012)
Publisher : Jurusan Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1205.227 KB) | DOI: 10.22146/jnteti.v1i2.16


Visual reconstruction and modeling of three dimensional (3-D) object is an emerging research topic in computer vision and photogrammetry fields. Nowadays, many commercial products are developed to obtain 3-D model of rigid object, starting from small ancient heritages to city landscape. Such commercial tools are very expensive and not accessible for education and research purpose. This paper aims to present a low-cost approach to generate a 3-D model from geometry of multiple two-dimensional (2-D) images using consumer-level Digital Single Lens Reflection (DSLR) camera. Direct Linear Transformation (DLT) algorithm was used to obtain 3-D point cloud. Texturization of 3-D object was generated by implementing Convex Hull and Random Sample Consensus (RANSAC) algorithms. Experimental result of small Merlion Singapore statue and large Herz-Jesu building shows that the proposed low-cost method is able to visually reconstruct small and large objects by using 10-20% feature points detected on 2D images.Rekonstruksi visual dan pemodelan objek tiga dimensi (3-D) adalah sebuah topik penelitian yang sedang berkembang pesat dalam bidang computer vision dan fotogrametri. Saat ini, banyak produk komersial dikembangkan untuk melakukan pemodelan objek 3-D dengan struktur rigid, mulai dari warisan sejarah berukuran kecil sampai dengan bentang darat perkotaan. Alat-alat komersial tersebut biasanya berbiaya tinggi dan tidak terjangkau apabila digunakan untuk tujuan pendidikan dan penelitian. Paper ini memperkenalkan sebuah metode berbiaya rendah untuk melakukan proses rekonstruksi objek 3-D dari unsur geometri beberapa citra dua dimensi (2-D) dengan menggunakan kamera Digital Single Lens Reflection (DSLR) yang banyak dijumpai di pasaran. Algoritma Direct Linear Transformation (DLT) digunakan untuk menghasilkan titik-titik 3-D. Proses teksturisasi objek 3-D dilakukan dengan memanfaatkan algoritma Convex Hull dan Random Sample Consensus (RANSAC). Hasil percobaan pada objek patung miniatur Merlion Singapore dan bangunan Herz-Jesu menunjukkan bahwa metode berbiaya rendah ini mampu merekonstruksi objek miniatur dan objek berukuran besar secara visual dengan memanfaatkan 10-20% titik-titik fitur yang terdeteksi pada citra 2-D.
Texture feature extraction for the lung lesion density classification on computed tomography scan image ., Hasnely; Nugroho, Hanung Adi; Wibirama, Sunu; Windarta, Budi; Choridah, Lina
Communications in Science and Technology Vol 1 No 1 (2016)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.1.1.2016.14


The radiology examination by computed tomography (CT) scan is an early detection of lung cancer to minimize the mortality rate. However, the assessment and diagnosis by an expert are subjective depending on the competence and experience of a radiologist. Hence, a digital image processing of CT scan is necessary as a tool to diagnose the lung cancer. This research proposes a morphological characteristics method for detecting lung cancer lesion density by using the histogram and GLCM (Gray Level Co-occurrence Matrices). The most well-known artificial neural network (ANN) architecture that is the multilayers perceptron (MLP), is used in classifying lung cancer lesion density of heterogeneous and homogeneous. Fifty CT scan images of lungs obtained from the Department of Radiology of RSUP Dr. Sardjito Hospital, Yogyakarta are used as the database. The results show that the proposed method achieved the accuracy of 98%, sensitivity of 96%, and specificity of 96%.
Automated localisation of optic disc in retinal colour fundus image for assisting in the diagnosis of glaucoma Listyalina, Latifah; Nugroho, Hanung Adi; Wibirama, Sunu; Oktoeberza, Widhia KZ
Communications in Science and Technology Vol 2 No 1 (2017)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21924/cst.2.1.2017.43


Optic disc (OD), especially its diameter together with optic cup diameter can be used as a feature to diagnose glaucoma. This study contains two main steps for optic disc localisation, i.e. OD centre point detection and OD diameter determination.  Centre point of OD is obtained by finding brightness pixel value based on average filtering.  After that, OD diameter is measured from the detected optic disc boundary.  The proposed scheme is validated on 30 healthy and glaucoma retinal fundus images from HRF database.  The results are compared to the ground truth images.  The proposed scheme obtains evaluation result (E) for healthy and glaucoma images is 0.23 and 0.21, respectively.  These results indicate successful implementation of automated OD localisation by detecting OD centre point and determining OD diameter.
Detection of malaria parasites in thick blood smear: A review Azif, Faza Maula; Nugroho, Hanung Adi; Wibirama, Sunu
Communications in Science and Technology Vol 3 No 1 (2018)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (211.443 KB) | DOI: 10.21924/cst.3.1.2018.75


Malaria adalah salah satu penyakit serius yang sering mengakibatkan kematian. Berdasarkan data dari organisasi kesehatan dunia (WHO), di tahun 2015, 90% kematian akibat malaria terjadi di benua Afrika, diikuti oleh Asia Tenggara dan negara – negara mediterania timur. Deteksi dini parasit plasmodium diperlukan untuk membantu proses diagnosis malaria. Seiring dengan berkembangnya teknologi informasi, proses diagnosis malaria melalui sediaan darah dapat terbantu dengan adanya teknik pengolahan citra digital. Dengan menggunakan citra digital sediaan darah merah, pada umumnya, identifikasi parasit dilakukan melalui beberapa tahap, yaitu pra-pemrosesan, segmentasi, ekstraksi fitur dan klasifikasi. Tulisan ini membandingkan metode – metode pengolahan citra untuk menentukan metode yang terbaik yang dapat diimplementasikan pada bidang deteksi parasit malaria pada sediaan darah tebal.
Wart treatment method selection using AdaBoost with random forests as a weak learner Putra, M. Azka; Setiawan, Noor Akhmad; Wibirama, Sunu
Communications in Science and Technology Vol 3 No 2 (2018)
Publisher : Komunitas Ilmuwan dan Profesional Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (272.523 KB) | DOI: 10.21924/cst.3.2.2018.96


Selection of wart treatment method using machine learning is being a concern to researchers. Machine learning is expected to select the treatment of warts such as cryotherapy and immunotherapy to patients appropriately. In this study, the data used were cryotherapy and immunotherapy datasets. This study aims to improve the accuracy of wart treatment selection with machine learning. Previously, there are several algorithms have been proposed which were able to provide good accuracy in this case. However, the existing results still need improvement to achieve better level of accuracy so that treatment selection can satisfy the patients. The purpose of this study is to increase the accuracy by improving the performance of weak learner algorithm of ensemble machine learning. AdaBoost is used in this study as a strong learner and Random Forest (RF) is used as a weak learner. Furthermore, stratified 10-fold cross validation is used to evaluate the proposed algorithm. The experimental results show accuracy of 96.6% and 91.1% in cryotherapy and immunotherapy respectively.
Rekonstruksi Objek 3D dari Multiple Images Rachmawati, Rachmawati; Hidayat, Risanuri; Wibirama, Sunu
Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI) Vol 2, No 1 (2013)
Publisher : Jurusan Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1115.087 KB) | DOI: 10.22146/jnteti.v2i1.27


Abstract - 3D reconstruction is a task of recovering 3D geometry and color information. There are two categories of 3D object reconstruction: active method, 3D model acquisition can be performed by laser scanner or structured light. Passive methods, reconstruct 3D models by image sequences from a single camera or multiple cameras. Object scanning often demand expensive equipment and special skill to operate. As a simple and low cost approach, 3D reconstruction based images became more popular among the researches. In this study apply passive reconstruction technique, the reconstruction of 3D objects made using images taken from different viewpoint leading to the same object using a digital camera.To determine the corresponding points of the two views used epipolar geometry and Direct Linear Triangulation algorithm (DLT). All required parameters are extracted from the image itself, without any calibration of the camera before. The reconstruction process can divided into four part: first, feature point extraction. Second estimate the fundamental matrix from point correspondences, third compute the camera matrix, and the end compute 3D point from image points. All the required parameters are recovered from the images. As objects of experiment used a miniatur of a statue. Experiment result show the residual error from estimation fundamental matrix is 9.9051 x10-04, and reprojection error 1.714 x 10-03 pixel. Visually, the reconstructed 3D model reseamble the shape of the original object.Intisari - Rekonstruksi 3D merupakan proses untuk memperoleh kembali informasi geometri 3D dan warna. Teknik rekonstruksi objek tiga dimensi terbagi menjadi 2 kategori, yaitu metode aktif: akuisisi model 3D dapat dilakukan dengan laser scanner atau cahaya terstruktur. Metode pasif: rekonstruksi model 3D dengan sekumpulan gambar dari sebuah atau beberapa kamera. Object scanning terkadang membutuhkan peralatan yang mahal dan keahlian khusus untuk mengoperasikan. Sebagai pendekatan yang sederhana dan murah, rekonstruksi objek berdasarkan gambar menjadi lebih popular bagi para peneliti. Pada penelitian ini menerapkan teknik rekonstruksi pasif, rekonstruksi objek 3D dilakukan dengan menggunakan citra yang diambil dari posisi yang berbeda yang mengarah ke obyek yang sama menggunakan sebuah kamera digital sederhana. Untuk menentukan titik-titik persamaan dari kedua citra tersebut digunakan epipolar geometry dan komputasi titik 3D menggunakan algoritma Direct Linear Triangulation (DLT). Semua parameter yang dibutuhkan diekstrak dari citra itu sendiri, tanpa dilakukan kalibrasi kamera sebelumnya. Tahapan rekonstruksi dapat dibagi menjadi empat bagian: pertama, ekstraksi titik fitur, kedua menghitung fundamental matrik dari titik – titik yang berkoresponden, ketiga menghitung matrik kamera dan terakhir mendapatkan titik-titik 3D untuk semua pasangan titik citra. Sebagai obyek penelitian adalah sebuah miniatur patung. Dari hasil rekonstruksi patung dari menggunakan citra dengan resolusi 1824 x 1368 pixel diperoleh residual error 9.9051 x 10-04 dan reproyeksi error 1.714 x 10-03. Secara visualisasi model 3D yang dihasilkan menyerupai bentuk obyek aslinya.Kata Kunci - rekonstruksi 3D, citra, matriks fundamental, epipolar geometry.