แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Sakulrat Thammathiwat. Fusion of segmented images using the level set method. Master's Degree(Electrical Engineering). Kasetsart University. Office of the University Library. : Kasetsart University, 2018.
Fusion of segmented images using the level set method
Name: Sakulrat Thammathiwat
Classification :.LCCS: TA1638.4
LCSH:
Image processing
-- Digital techniques
LCSH:
Image processing
LCSH:
Image segmentation
Abstract:
We proposed a novel approach for fusing several segmentations of an image into a single result. The goal of this fusion method is to obtain a more accurate and reliable segmentation, since segmentation algorithms have been continuously proposed. In general, these segmentation algorithms may not be optimum in all situations. One idea is to develop a new algorithm to deal with every specific problem. However, this approach is not practical. Our idea is to combine the results from different segmentation together by measuring the similarity between the resulting segmented image and each input segmentations. To achieve this goal, we apply a standard similarity measurement called Rand index together with a level set method. The level set functions are used to represent different combining segmented images where the Rand Index is used to compute the similarity score against the input segmented images. In this thesis, we also propose a low-level fusion algorithm based on the Chair-Varshney fusion rule in order to understand the basic of level set framework and fusion technique. The performances of both proposed algorithms are represented on various groups of synthetic images and on real images. Furthermore, four featured points are also demonstrated in our experiments i.e., requirement of prior knowledges, number of region, region numbers of each segmentation, and quantities of image segmentation to be fused.
Kasetsart University. Office of the University Library
Address:
Bangkok
Email:
tdckulib@ku.ac.th
Name: Teerasit Kasetkasem
Role:
Thesis Advisor
Created:
2018
Modified:
2025-07-09
Issued:
2025-07-09
วิทยานิพนธ์/Thesis
application/pdf
URL: https://www.lib.ku.ac.th/KUthesis/2561/sakulrat-tha-all.pdf
CallNumber:
TA1638.4 .S25
eng
DegreeName: Master of Engineering
Level: Master's Degree
Descipline: Electrical Engineering
Grantor: Kasetsart University
©copyrights Kasetsart University
RightsAccess:
ใช้เวลา
0.028288 วินาที
Sakulrat Thammathiwat
| Title | Contributor | Type |
|---|---|---|
| Fusion of segmented images using the level set method
มหาวิทยาลัยเกษตรศาสตร์ Sakulrat Thammathiwat | Teerasit Kasetkasem | วิทยานิพนธ์/Thesis |
Teerasit Kasetkasem