Akhtar, Mohammad Wasim (1991) Towards an optimal accumulator size for the Hough transform. Masters thesis, King Fahd University of Petroleum and Minerals.
Hough Transform (HT) is widely used in Computer Vision. HT is a mapping from the image plane onto the parameter space. It can detect any shape which can be defined by a parametric equation. When HT is used to detect straight line segments in images, the conventional approach only gives information regarding the parameters defining the line segment. It does not give the exact position of the line segment. Some authors have developed procedures to obtain the complete line segment description using the HT, but their methods are all highly compute-bound and require large storage space. In this thesis a new approach for obtaining the complete line segment description from the information in the accumulator array is developed and a criterion for an optimal accumulator size is suggested. The developed approach reduces the computational complexity of the HT. The new approach has been tested on synthetic images without noise, synthetic images with noise, and also on real world images which inevitably contain noise.
|Item Type:||Thesis (Masters)|
|Divisions:||College Of Engineering Sciences > Electrical Engineering Dept|
|Creators:||Akhtar, Mohammad Wasim|
|Committee Advisor:||Atiquzzaman, Mohammad|
|Committee Members:||Biyari, Khaled H. and Bettayeb, Mammar and Al-Akhdhar, Syed Zaki|
|Deposited By:||KFUPM ePrints Admin|
|Deposited On:||22 Jun 2008 16:43|
|Last Modified:||25 Apr 2011 08:57|
Repository Staff Only: item control page