Spatial-frequency approaches to texture analysis
Spatial-frequency methods have been extensively and successfully employed by many computer vision researchers to texture analysis in the last two decades. The focus of this thesis is on the research work carried out based on such approaches. First, application of Gabor filters to texture analysis is...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Theses and Dissertations |
| 語言: | English |
| 出版: |
2008
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10356/13253 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Spatial-frequency methods have been extensively and successfully employed by many computer vision researchers to texture analysis in the last two decades. The focus of this thesis is on the research work carried out based on such approaches. First, application of Gabor filters to texture analysis is investigated. A filter selection algorithm for texture recognition has been developed to select a small subset of Gabor filters from a pre-defined Gabor filter bank. The filter selection is based on the discriminative power of each individual Gabor filter in regard to the recognition of all the textures in an image database. The proposed filter se-lection algorithm is demonstrated to be capable of selecting more discriminative filter through texture classification and retrieval experiments. |
|---|