A SIFT descriptor with color information for object recognition based on log color space
碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 99 === The scale Invariant feature Transform (SIFT) is an effective and popular method of extracting key-point features of the gray image. Recently, one of the topic of improving SIFT is to incorporate the color information into SIFT. In this thesis, SIFT is carried ou...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2011
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/81068722934459353523 |
| Summary: | 碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 99 === The scale Invariant feature Transform (SIFT) is an effective and popular method of extracting key-point features of the gray image. Recently, one of the topic of improving SIFT is to incorporate the color information into SIFT. In this thesis, SIFT is carried out based on the log color space. It turns out that the proposed approach is more robust to the change of illumination condition. The proposed approach has tested against synthesized images and the ALOI image database, a public image data set.
Experimental results have shown that the proposed approach is more precise than SIFT and some color- invariant-based SIFT when illumination or color temperature changes.
|
|---|