A programming framework to implement rule-based target detection in images

Download
index.pdf
2008
Şahin, Yavuz
Show full item record
156
views
79
downloads
An expert system is useful when conventional programming techniques fall short of capturing human expert knowledge and making decisions using this information. In this study, we describe a framework for capturing expert knowledge under a decision tree form and this framework can be used for making decisions based on captured knowledge. The framework proposed in this study is generic and can be used to create domain specific expert systems for different problems. Features are created or processed by the nodes of decision tree and a final conclusion is reached for each feature. Framework supplies 3 types of nodes to construct a decision tree. First type is the decision node, which guides the search path with its answers. Second type is the operator node, which creates new features using the inputs. Last type of node is the end node, which corresponds to a conclusion about a feature. Once the nodes of the tree are developed, then user can interactively create the decision tree and run the supplied inference engine to collect the result on a specific problem. The framework proposed is experimented with two case studies; "Airport Runway Detection in High Resolution Satellite Images" and "Urban Area Detection in High Resolution Satellite Images". In these studies linear features are used for structural decisions and Scale Invariant Feature Transform (SIFT) features are used for testing existence of man made structures.
Computer engineering., General Civil Engineering.
http://etd.lib.metu.edu.tr/upload/12610213/index.pdf
https://hdl.handle.net/11511/18154
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

A Content-Boosted Collaborative Filtering Approach for Movie Recommendation Based on Local and Global Similarity and Missing Data Prediction
Özbal, Gozde; Karaman, Hilal; Alpaslan, Ferda Nur (Oxford University Press (OUP), 2011-09-01)
Most traditional recommender systems lack accuracy in the case where data used in the recommendation process is sparse. This study addresses the sparsity problem and aims to get rid of it by means of a content-boosted collaborative filtering approach applied to a web-based movie recommendation system. The main motivation is to investigate whether further success can be obtained by combining 'local and global user similarity' and 'effective missing data prediction' approaches, which were previously introduce...
A remote sensing computer-assisted learning tool developed using the unified modeling language
Friedrich, J; Karslıoğlu, Mahmut Onur (Elsevier BV, 2004-07-01)
The goal of this work has been to create an easy-to-use and simple-to-make learning tool for remote sensing at an introductory level. Many students struggle to comprehend what seems to be a very basic knowledge of digital images, image processing and image arithmetic, for example. Because professional programs are generally too complex and overwhelming for beginners and often not tailored to the specific needs of a course regarding functionality, a computer-assisted learning (CAL) program was developed base...
A GPS/GIS based line of balance method for planning and control of construction projects
Uysal, Furkan; Sönmez, Rifat; Department of Civil Engineering (2007)
In construction industry Gantt charts, network methods and Line of Balance (LOB) methods are generally used for planning and control of projects. Networking techniques such as Critical Path Method (CPM) and Program Evaluation and Review Technique (PERT) require technical knowledge and could be difficult to implement without proper scheduling background. Gantt charts and LOB techniques are usually easier to implement, however, similar to network techniques these techniques lack visualization. A graphical bas...
Integrating estimation of distribution algorithms versus Q-learning into Meta-RaPS for solving the 0-1 multidimensional knapsack problem
Arin, Arif; Rabadi, Ghaith (Elsevier BV, 2017-10-01)
Finding near-optimal solutions in an acceptable amount of time is a challenge when developing sophisticated approximate approaches. A powerful answer to this challenge might be reached by incorporating intelligence into metaheuristics. We propose integrating two methods into Meta-RaPS (Metaheuristic for Randomized Priority Search), which is currently classified as a memoryless metaheuristic. The first method is the Estimation of Distribution Algorithms (EDA), and the second is utilizing a machine learning a...
An equivalent linearization procedure for seismic response prediction of mdof systems
Günay, Mehmet Selim; Sucuoğlu, Haluk; Department of Civil Engineering (2008)
Nonlinear response history analysis is accepted as the most accurate analytical tool for seismic response determination. However, accurate estimation of displacement responses using conceptually simple, approximate analysis procedures is preferable, since there are shortcomings in the application of nonlinear response history analysis resulting from its complexity. An equivalent linearization procedure, which utilizes the familiar response spectrum analysis as the analysis tool and benefits from the capacit...
Citation Formats
Y. Şahin, “A programming framework to implement rule-based target detection in images,” M.S. - Master of Science, Middle East Technical University, 2008.
METU IIS - Integrated Information Service open@metu.edu.tr