1 AIT Asian Institute of Technology

Landuse mapping using self organizing map

AuthorDjoko Budiyanto Setyahadi
Call NumberAIT Thesis no. CS-97-5
Subject(s)Image processing--Digital techniques
Land use

NoteA thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Advanced Technology
PublisherAsian Institute of Technology
AbstractInterpretation technique of remote sensing image require extraction of not only features but also the knowledge that aid to identify objects. In computer vision, segmentation of the image into its component are performed by extraction of certain features. Clustering, using unsupervised classification, is one kind of image analysis techniques to make the segmentation of the image. Interpretation is the main problem which is frequently found when unsupervised classification algorithm is applied. The problem is due to process unsupervised classification which is based on the spectral value, while interpretation of the remote sensing object can not . be based only on the spectral value. To over come the domain, the knowledge should be generated and added after classification is completed. In this research, SOM neural network is investigated by simulating the neighborhood size, network size and learning rate. Simulating is due to find the appropriate parameter of SOM neural network in order to classify the image, generate the knowledge, and interpret the remote sensing image to be Janduse map. The result is measured and compared with ยท ISODATA method. The result of this research shows that the performance of SOM neural network is better than ISODAT A method, both on the exploration cluster and accuracy assessment.
Year1997
TypeThesis
SchoolSchool of Advanced Technologies (SAT)
DepartmentDepartment of Information and Communications Technologies (DICT)
Academic Program/FoSComputer Science (CS)
Chairperson(s)Sadananda, Ramakoti;
Examination Committee(s)Yulu, Qi ;Honda, Kiyoshi ;Pattarasine Bhattarakosol ;
Scholarship Donor(s)Atma Jaya University Yogyakarta ;
DegreeThesis (M.Eng.) - Asian Institute of Technology, 1997


Usage Metrics
View Detail0
Read PDF0
Download PDF0