QQ客服 官方微博 反馈留言

浏览/检索结果: 共6条，第1-6条 帮助 限定条件 发表日期：2012     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 A fast target recognition algorithm based on MSA and MSR (EI CONFERENCE) 会议论文 2012 International Conference on Industrial Control and Electronics Engineering, ICICEE 2012, August 23, 2012 - August 25, 2012, Xi'an, China Huang J.; Wang Y.; Ji H.; Liu G. 收藏  |  浏览/下载：23/0  |  提交时间：2013/03/25 This paper presents a new fast target recognition algorithm  the proposed method is based on Multi-scale Auto convolution(MSA) and Multi-scale Retinex(MSR). As shown by the comparison with original MSA  it appears that this new technique solves the problem that MSA algorithm is sensitive to illumination and the computational load is significantly reduced to 1/8th of that of the original MSA algorithm  it is also robust to affine transform  light projective transform  noise  thin fog  occlusion and illumination change. the performed experiments show that it has fast searching speed  and can accurately recognize and locate target in real scenes. 2012 IEEE.   Image registration based on Mexican-hat wavelets and pseudo-Zernike moments (EI CONFERENCE) 会议论文 2012 World Automation Congress, WAC 2012, June 24, 2012 - June 28, 2012, Puerto Vallarta, Mexico Ding N.; Liu Y. 收藏  |  浏览/下载：28/0  |  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.   基于模糊控制的ASIFT图像特征优化算法 期刊论文 2012 蔡国榕; 李绍滋; 陈水利; 吴云东; 苏松志 收藏  |  浏览/下载：2/0  |  提交时间：2016/05/17 SIFT特征  仿射变换  Nelder-Mead单纯形法  模糊控制  SIFT Feature  Affine Transform  Nelder-Mead Simplex  Fuzzy Control   Blind super-resolution reconstruction algorithm under affine motion model 期刊论文 Pattem Recognition and Aitificial Intelligence,, 2012, 卷号: 25(4), 期号: 2012年04期, 页码: pp 648-655 (EI) 作者:  Zhang, Xue-Song;  Jiang, Jing;  Peng, Si-Long 收藏  |  浏览/下载：14/0  |  提交时间：2017/01/13 Affine Transform / blind Super-resolution (Bsr / motion Estimation / blur    Affine invariant image watermarking using intensity probability density-based Harris Laplace detector 期刊论文 Journal of Visual Communication and Image Representation, 2012, 卷号: Vol.23 No.6, 页码: 892-907 作者:  Xiang-yang Wang;  Pan-pan Niu;  Hong-ying Yang;  Li-li Chen 收藏  |  浏览/下载：4/0  |  提交时间：2019/02/27 Image  watermarking  Geometric  distortion  Intensity  probability  density  Affine  invariant  local  ellipse  region  Nonsubsampled  contourlet  transform  Harris–Laplace  detector  Image  feature  point  Synchronization  error   Using incremental subspace and contour template for object tracking 期刊论文 JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2012, 卷号: 35, 页码: 1740-1748 作者:  Yin, Jihao;  Fu, Chongyang;  Hu, Jiankun 收藏  |  浏览/下载：1/0  |  提交时间：2020/01/06 Contour model  Object tracking  Incremental learning  Affine transform