Normalized Cut Based Texture Segmentation System
碩士 === 中華大學 === 電機工程學系碩士班 === 89 === Image segmentation, which partitions images into homogeneous regions, is an important task in many computer vision applications. Typically, differences in gray levels and/or colors alone are not sufficient for segmenting images of interest. This problem may be so...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2001
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/03881273508111843299 |
| Summary: | 碩士 === 中華大學 === 電機工程學系碩士班 === 89 === Image segmentation, which partitions images into homogeneous regions, is an important task in many computer vision applications. Typically, differences in gray levels and/or colors alone are not sufficient for segmenting images of interest. This problem may be solved to a certain degree by taking account of the texture information. One of the commonly used approaches to extracting texture features is the frequency approach. In this thesis, we used Gabor filters to extract texture features in various frequency bands. Based on these features, the Normalized cut measure of similarity between pixels are used to partition images such that the disassociation between different textures and the association within similar texture are to be maximized simultaneously. We also developed a texture segmentation system in which the Gabor filter based feature space is transformed into the Normalized cut based feature space by solving the associated generalized eigen-system efficiently. The performance improvement can be demonstrated by the experimental results on segmentation of some Brodatz textures.
|
|---|