Tumor detection based on enhanced hill climbing method
Image segmentation is good way to analyze information in various fields of life. Image processing, especially image segmentation is very important and beneficial especially for the medical image segmentation and many other fields, from the application of segmentation know how the segmentation is imp...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2010
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/11058/6/AliTahaYaseenMFSKSM2010.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Image segmentation is good way to analyze information in various fields of life. Image processing, especially image segmentation is very important and beneficial especially for the medical image segmentation and many other fields, from the application of segmentation know how the segmentation is important in our life. Image segmentation is the process of partitioning a digital image into sets of pixels. The aim of recognition system is to automatically identify the brain and extract the tumor from it. Several approaches have been proposed for medical segmentation. Some of the methods use color and brightness to reduce the complexity of the problem. Although such approaches solve the detect edges of regions. They are not able to handle almost any variation on the brain physical structure. There are many techniques have been proposed for tumor brain segmentation and Hill climbing is one of these techniques. The combination of the different approaches for the segmentation of brain images is presented in this project. Propose a color-based segmentation method that uses the K-means clustering technique with Hill climbing method to track tumor objects in magnetic resonance (MR) brain images, K-means clustering is used to cluster the image from gray to RGB scale while Hill climbing has been applied for the segmentation after that to overcome the problem with empty holes and Incoherent borders in the image , this project can successfully achieve segmentation for MR brain images to help pathologists distinguish exactly lesion size and region. |
|---|