机构

• 长春光学精密机械与物... [1]
• 自动化研究所 [1]

采集方式

• OAI收割 [2]

内容类型

• 会议论文 [1]
• 学位论文 [1]

发表日期

• 2015 [1]
• 2012 [1]

学科主题

筛选

浏览/检索结果: 共2条，第1-2条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 基于红外光谱非线性的相关校正模型研究 学位论文  OAI收割 工学博士, 中国科学院自动化研究所: 中国科学院大学, 2015 作者:  单鹏 收藏  |  浏览/下载：104/0  |  提交时间：2015/09/02 红外光谱  经典最小二乘  总体最小二乘  偏最小二乘  多元校正  分片样条变换  非线性  Infrared spectrum  Classical least squares  Total least squares  Partial least squares  Multivariate calibration  Slice transform  Nonlinearity   Image registration based on Mexican-hat wavelets and pseudo-Zernike moments (EI CONFERENCE) 会议论文  OAI收割 2012 World Automation Congress, WAC 2012, June 24, 2012 - June 28, 2012, Puerto Vallarta, Mexico 作者:  Liu Y.;  Liu Y.;  Liu Y. 收藏  |  浏览/下载：37/0  |  提交时间：2013/03/25 Image registration is a key technique in pattern recognition and image processing  and it is widely used in many application areas such as computer vision  remote sensing  image fusion and object tracking. A method for image registration combining Mexican-hat wavelets and pseudo-Zernike moments is proposed. Firstly  feature points are extracted using scale-interaction Mexican-hat wavelets in the reference image and sensed image respectively. Then  pseudo-Zernike moments are used to match them and classical RANSAC used to eliminate the wrong matches. And then  the well match points are used to estimate the best affine transform parameters by least squares minimization. At last  the sensed image is transformed and resampled to accomplish the image registration. The experiments indicate that the proposed algorithm extracts feature points and matches them exactly and eliminates wrong matched points effectively and achieves nice registration results. 2012 TSI Press.