Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
[ABSTRAK
Penelitian mengenai segmentasi karakter merupakan proses awal dalam melakukan analisis isi naskah manuskrip Jawa. Segmentasi karakter pada citra naskah sangatlah penting untuk proses transliterasi naskah beraksara Jawa menjadi huruf Latin secara otomatis oleh komputer.

Kertas pada naskah sudah rapuh dikarenakan umur naskah yang tua sehingga menyebabkan kontras yang rendah dan munculnya noise antara teks dan background. Serta warna tinta yang sudah memudar berpengaruh pada kontras karakter pada naskah. Dimungkinkan juga terjadi ambigu hasil segmentasi karakter dikarenakan adanya keanekaragaman ukuran karakter dan adanya jarak spasi pada satu karakter.

Langkah-langkah segmentasi karakter yang dilakukan dalam penelitian ini adalah image acquisition, Gaussian filtering, binerisasi citra dengan algoritma Wolf-Jolion, segmentasi baris dengan metode vertical profile projection (VPP) dan Radon transform serta rule deteksi objek dengan connected component analysis, kemudian segmentasi karakter dengan metode horizontal profile projection.

Evaluasi segmentasi baris dilakukan dengan perhitungan nilai hit rate untuk empat kriteria, yaitu Correct untuk hasil yang benar, Line Including Outlier Script (LIOS) untuk hasil segmentasi yang memiliki aksara dari baris lain, Truncated Line (TL) untuk baris yang terpotong, dan Mix (LIOS+TL) untuk baris yang memiliki aksara dari baris lain dan juga terpotong. Hasil segmentasi baris yang benar (Correct) dengan metode VPP adalah 0.77 dan dengan metode Radon transform adalah 0.8. Hal ini dikarenakan perhitungan jumlah piksel hitam pada Radon transform berdasarkan sudut tertentu, sedangkan pada VPP perhitungan jumlah piksel hitam hanya berdasarkan satu baris saja.

Evaluasi hasil segmentasi karakter dilakukan dengan perhitungan nilai hit rate untuk dua kriteria, yaitu Readable untuk karakter yang dapat dibaca dan Unreadable untuk karakter yang tidak terbaca. Hasil segmentasi karakter dengan citra baris hasil dari vertical profile projection adalah 0.60245 dan nilai hit rate hasil segmentasi karakter dengan citra baris dari Radon transform adalah 0.60036. Hasil segmentasi karakter dengan input citra baris hasil segmentasi Radon transform hasilnya lebih rendah dikarenakan terdapat beberapa hasil segmentasi baris yang tumpang tindih (2 baris tersegmentasi menjadi 1 baris). Sehingga horizontal profile projection gagal dalam melakukan identifikasi lokasi karakter pada baris tersebut.;

---

ABSTRACT
Research on the segmentation of character is the initial process in conducting an analysis of the Javanese manuscript. Character segmentation in the image of a manuscript is essential to the process of transliterating Javanese script into Latin characters automatically by computer.

Paper on a manuscript already fragile due to age old script causing the low contrast and the emergence of noise between text and background. As well as the color of the ink that's been fading effect on contrasting characters in the script. It is possible occur ambiguous character segmentation results due to the diversity of character size and distance of space on a single character.

Segmentation character steps that are undertaken in this research are image acquisition, Gaussian filtering, image binarization with Wolf-Jolion algorithm, segmentation line with a method of vertical profile projection (VPP) and Radon transform and the rule detection of objects by connected component analysis, then segmentation characters by horizontal profile projection method.

The evaluation of the segmentation of the line carried out by calculation the hit rate to four criteria , that is Correct for result right, Line Including Outlier Script (LIOS) for the results of the segmentation of having script of the other line, Truncated Line (TL) for line truncated, and Mix (LIOS + TL) for line having script of the other line and also cut off. The results of segmentation line are properly (Correct) by VPP method is 0.77 and with Radon transform method is 0.8. It was because the calculations the number of pixels black on radon transform based on certain angles while in VPP calculating the number of black pixels only on one line.

Evaluation of the results of the segmentation of the character performed with calculation of the value of a hit rate to two criteria namely Readable for characters that can be read and Unreadable for the character of being illegible. The results of the segmentation of character with the line images result of the vertical profile projection is 0.60245 and hit rate value as results of the segmentation of character with the line images result of the Radon transform is 0.60036. The results of the segmentation of character with the line images result of the Radon transform more low because there are the outcome of several segmentation lines that overlap (2 lines segmented become a single line). So that horizontal profile projection fail in doing identifying location of the characters on the line. , Research on the segmentation of character is the initial process in conducting an analysis of the Javanese manuscript. Character segmentation in the image of a manuscript is essential to the process of transliterating Javanese script into Latin characters automatically by computer. Paper on a manuscript already fragile due to age old script causing the low contrast and the emergence of noise between text and background. As well as the color of the ink that's been fading effect on contrasting characters in the script. It is possible occur ambiguous character segmentation results due to the diversity of character size and distance of space on a single character. Segmentation character steps that are undertaken in this research are image acquisition, Gaussian filtering, image binarization with Wolf-Jolion algorithm, segmentation line with a method of vertical profile projection (VPP) and Radon transform and the rule detection of objects by connected component analysis, then segmentation characters by horizontal profile projection method. The evaluation of the segmentation of the line carried out by calculation the hit rate to four criteria , that is Correct for result right, Line Including Outlier Script (LIOS) for the results of the segmentation of having script of the other line, Truncated Line (TL) for line truncated, and Mix (LIOS + TL) for line having script of the other line and also cut off. The results of segmentation line are properly (Correct) by VPP method is 0.77 and with Radon transform method is 0.8. It was because the calculations the number of pixels black on radon transform based on certain angles while in VPP calculating the number of black pixels only on one line. Evaluation of the results of the segmentation of the character performed with calculation of the value of a hit rate to two criteria namely Readable for characters that can be read and Unreadable for the character of being illegible. The results of the segmentation of character with the line images result of the vertical profile projection is 0.60245 and hit rate value as results of the segmentation of character with the line images result of the Radon transform is 0.60036. The results of the segmentation of character with the line images result of the Radon transform more low because there are the outcome of several segmentation lines that overlap (2 lines segmented become a single line). So that horizontal profile projection fail in doing identifying location of the characters on the line. ]

Abstrak :
ABSTRAK Proses pemindaian dini saat ini masih dilakukan dengan Computed Tomography Scan atau Magnetic Resonance Imaging. Namun, alat pemindai tersebut memiliki biaya yang mahal dan ukuran yang besar. Pencitraan gelombang mikro merupakan salah satu teknik tomografi alternatif yang dapat menutupi kekurangan tersebut. Sementara itu, sistem pencitraan medis membutuhkan jumlah pengukuran yang cukup banyak untuk mendapatkan citra hasil rekonstruksi yang baik. Untuk mengurangi jumlah pengukuran, penelitian ini mengusulkan pendekatan Compressive Sensing CS untuk aplikasi pencitraan gelombang mikro. Proses pemindaian dilakukan pada perangkat lunak Computer Simulation Technology dengan objek uji berupa phantom kubus dua lapis dengan permitivitas yang berbeda. Agar sesuai dengan kerangka CS , matriks pembobotan Discrete Radon Transform dipilih sebagai matriks proyeksi. Discrete Cosine Transform dan Basis Pursuit dipilih sebagai matriks sparse dictionary dan algoritma rekonstruksi sinyal sparse. Pada proses pemindaian, jumlah translasi dan rotasi divariasikan untuk menguji kinerja CS. Data pengukuran S21 berhasil direkonstruksi menjadi citra dengan pendekatan CS. Hasil rekonstruksi menunjukkan bahwa penambahan jumlah translasi dan rotasi dapat meningkatkan kualitas citra hasil rekonstruksi, meskipun tidak terdapat hubungan yang linear antara keduanya. Secara kualitatif dan kuantitatif, citra hasil rekonstruksi menggunakan CS memiliki kualitas yang lebih baik dibandingkan dengan yang direkonstruksi menggunakan algoritma Filtered Back Projection dan Simultaneous Algebraic Reconstruction Technique. Sebagai tambahan, CS terbukti dapat merekonstruksi data pengukuran sebenarnya dari phantom fisik menjadi sebuah citra.

---

ABSTRACT
Early detection is still generally performed by using Computed Tomography scan or Magnetic Resonance Imaging. However, those modalities have high production costs and considerable size. Microwave Imaging is one of the alternative tomography techniques that can overcomes those aforementioned problems. Meanwhile, the medical imaging systems require a great amount of data measurements to obtain a good reconstructed image. In order to reduce the number of measurements, this research proposes a Compressive Sensing CS approach for microwave imaging application. The scanning process is conducted on Computer Simulation Technology software. A two layer cube phantom with different permittivity is used as the scanned object. To meet the framework of CS, weight matrix of Discrete Radon Transform is utilized as projection matrix. Discrete Cosine Transform and Basis Pursuit are selected as sparse dictionary matrix and sparse reconstruction algorithm respectively. In the data acquisition process, the number of translations and rotations is varied to test the performance of CS. The measured S21 data are successfully reconstructed by CS approach into an image. The reconstruction results show that adding the number of translations and rotations can improve the quality of the reconstructed image, although there is no linear relationship between them. Qualitatively and quantitatively, the image reconstructed using CS has a better quality compared to that reconstructed using Filtered Back Projection and Simultaneous Algebraic Reconstruction Technique algorithm. In addition, CS is proved to be able to reconstruct the real measurement data from the physical phantom into an image

Abstrak :
Aplikasi teknik biomedis berkembang dengan cepat dalam beberapa dekade terakhir. Salah satu aplikasi dalam teknik biomedis adalah pencitraan medis yang saat ini sudah diadopsi dan beberapa masih diteliti secara luas. Beberapa teknologi yang sudah diadopsi seperti CT scan, sinar-X, MRI, PET dan SPECT masih memiliki dimensi yang relatif besar, tidak portable dan biaya pembuatan serta pemeliharan yang mahal. Sekarang ini, modality baru yang sedang berkembang seperti pencitraan gelombang mikro (microwave imaging) menawarkan beberapa kelebihan lain terutama biaya yang murah, portable, dan bersifat non-invasive dan non-intrusive. Di dalam teknologi pencitraan medis, beberapa diantaranya menggunakan metode rekonstruksi citra yang berbasis algoritma proyeksi balik (back projection). Oleh karena lamanya proses pengambilan data ketika proses pemindaian (scanning), maka diperlukan sistem akuisisi data yang dapat mengambil data pemindaian secara otomatis. Dalam skripsi ini, dirancang sebuah sistem akuisisi data otomatis untuk pencitraan gelombang mikro yang berbasis algoritma proyeksi balik yang memanfaatkan transformasi Radon. Sistem yang dirancang berupa perpaduan rancangan perangkat keras dan perangkat lunak sehingga menghasilkan integrasi kedua perangkat dalam sebuah sistem akuisisi data pemindaian gelombang mikro. Perangkat lunak yang digunakan berbasis LabVIEW dan board Arduino sebagai interface dalam pengendalian rancangan sistem akuisisi. Pengujian sistem akuisisi data, dilakukan dengan menempatkan sebuah model phantom fisik homogen di antara dua buah antena dipole (sebagai transmitter & receiver) untuk dibandingkan dengan hasil simulasi dengan CST Microwave Studio pada frekuensi 3 GHz dan 5 GHz. Berdasarkan hasil pengujian sistem akuisisi data, diperoleh hasil bahwasanya sistem memiliki tingkat akurasi (step minimum) translasi sebesar 0,5 mm saat proses pemindaian objek. Hasil pembacaan data akuisisi yang diperoleh memiliki kesalahan rata-rata kurang dari 6% dibandingkan dengan hasil simulasi. ...... In few current decades, biomedical engineering applications are growing rapidly, which medical imaging is one of biomedical engineering applications that is currently widely adopted and studied for further improvement. Some existing technologies such as CT scan, X-ray, MRI, PET and SPECT are considerably still bulky, non-portable and relatively high production and maintenance cost. A new growing modality called microwave imaging offers some other advantages especially low cost, portable, which still maintain on non-invasively and non-intrusively technique. In some medical imaging systems usually still use a back projection algorithm to reconstruct the image. Due to the imaging system that uses back projection method takes relatively long scanning process, hence, data retrieval process is required to be performed by an automatically data acquisition system. In this bachelor thesis, an automatic data acquisition system is designed for microwave imaging purpose by using back projection algorithm that employing Radon transform. The acquisition system is designed as a blend of hardware design and software resulting in the integration of the both in a data acquisition system for microwave imaging. The software developed is a LabVIEW-based and Arduino board is set as an interface for controlling the designed acquisition system. In order to validate the data acquisition system, a homogeneous physical phantom is placed between two dipole antennas (as a transmitter and receiver) and the measured result is compared to the the simulation with CST Microwave Studio at the frequency of 3 GHz and 5 GHz. According to the testing results from the proposed data acquisition system, the system has an accuracy rate (minimum step) by 0.5 mm of the translation when it scans the object. In addition, an average error of the retrieved data from the acquisition system is less than 6% compared with the simulation results.