Barcode |
|
Judul English |
|
Examiners |
|
Head of post graduat |
|
Tim penguji 3 |
Dana Indra Sensuse |
No. Induk |
|
Tim penguji 4 |
Bobby A.A. Nazief |
Kata Kunci |
Segmentation, classification, SAR, PCNN, texture. |
Pembimbing 3 |
|
Pembimbing 2 |
Aniati Murni |
Kopromotor |
Muhammad Rahmat Widyanto |
Tahun buku |
2009 |
Barcode RFID baru |
11627474 |
Tim penguji 1 |
Belawai H. Widjaja |
Promotor |
Aniati Murni Arymurthy |
Abstrak Indonesia |
Telah dilakukan penelitian metodologi segmentasi dan klasifikasi citra
synthetic aperture radar (SAR) berdasarkan Pulse Coupled Neural Networks (PCNN) dikombinasikan dengan ciri tekstur. Langkah awal penelitian ialah mencari nilai parameter optimal persamaan PCNN. Segmentasi citra dilakukan menggunakan tiga macam metoda yang diusulkan yaitu pertama berdasarkan PCNN yang nilai parameternya telah dibuat optimal, kedua yaitu berdasarkan modifikasi proses iterasi PCNN dan ketiga berdasarkan modifikasi persamaan PCNN. Hasil segmentasi tiga teknik ini dapat memisahkan wilayah sesuai ground truth, tetapi pada jumlah iterasi tertentu masih terjadi tumpang tindih. Klasifikasi berdasarkan PCNN dilakukan dua tahap yaitu pertama mengekstraksi ciri tekstur citra. Ekstraksi ciri ini menggunakan perhitungan Grey Level Co-occurrence Matrix (GLCM). Dipilih tiga macam ciri yaitu dissimilarity, correlation dan angular second moment. Tiga ciri ini menjadi masukan pada PCNN untuk
diiterasi. Hasil yang sangat menonjol dari rangkaian eksperimen ini ialah didapatkannya nilai optimal parameter persamaan PCNN yang tegar, metoda modifikasi iterasi persamaan PCNN yang dapat menghindari terjadinya tumpang tindih pada dua kelas wilayah hasil segmentasi, modifikasi persamaan PCNN menjadi empat persamaan yang dapat mempercepat segmentasi, dan hasil yang menonjol lainnya ialah dapat digunakannya PCNN ini untuk klasifikasi citra SAR yang bertekstur dan multi wilayah setelah dikombinasikan dengan ciri tekstur dan ketepatan klasifikasi berdasarkan PCNN yang diusulkan mencapai 91,58% untuk pita L, 88, 31% untuk pita C dan 85,33% untuk pita P. |
Cat. Umum |
|
Judul |
Metodologi segmentasi dan klasifikasi citra synthetic aperture radar berdasarkan pulse coupled neural networks dikombinasikan dengan ciri tekstur |
Co-Supervisor |
|
Subjek |
Image compression--Data processing; Neural network computers |
Pembimbing 1 |
|
Examiners 6 |
|
Examiners 5 |
|
Examiners 4 |
|
Supervisor |
|
Examiners 3 |
|
Examiners 2 |
|
Examiners 1 |
|
Bibliografi |
|
Pengarang |
Harwikarya; |
Co-Supervisor 1 |
|
Cat. Karya |
|
Tim Penguji 6 |
|
Timpenguji 2 |
Heru Suhartanto |
Tim Penguji 7 |
|
Tim Penguji 5 |
Marimin |
Co promotors |
|
chair Person |
|
Tanggal Datang |
29/07/2009 |
Asal |
|
Kopromotor 1 |
|
NPM |
920500005Y |
Abstrak English |
Study Program : Computer Science Title : Segmentation and Classification of Synthetic Aperture Radar Methodology Based on Pulse Coupled Neural Networks and Features Texture. The new methodology on segmentation and classification of Synthetic Aperture Radar (SAR) based on Pulse Coupled Neural Networks (PCNN) and features texture was proposed in this dissertation. The first step of this research is optimization the parameters of the PCNN. The segmentation is based on new methods which proposed in this dissertation. First by iterating the images used optimal PCNN, the second method by modifying the iteration of the PCNN, and the third method by modifying the equations of the PCNN. The results of these experiments are good enough, but in one of some iterations the result was overlap, in this case two area of the image were appeared in the binary image. The classification based on PCNN would be in two steps, first was the features extraction. The features were extracted by using the Gray Level Co-occurrence Matrix (GLCM). Three features, dissimilarity, correlation and angular second moment were selected to be processed by the PCCNN. The significant results of the experiments are, optimal variables of the PCNN which are robust, the new method of iteration of the PCNN which be able to avoid over lapping in segmentation, the new method of modification PCNN equation could increases the speed of segmentation and classification, and new method the application of PCNN in the segmentation and classification of the textural and multi region SAR images. Total accuracy for L band is 91,58%, C band is 88,31% and P band is
Key words :Segmentation, classification, SAR, PCNN, texture. |
Pengarang 2 |
|
Chair of examiner |
|
Fisik |
xvii+130 hlm;il.+lamp.:20 cm. |
Bahasa |
Ind. |
Lulus Semester |
|
Penerbitan |
Depok: Fakultas Ilmu Komputer UI, 2009 |
No. Panggil |
DIS-018 (Softcopy DIS-009) |