Invariant representation for blur and down-sampling transformations
文献类型：会议论文
| 作者 | Gu HX(谷鹄翔)1 ; Leibo Joel2; Anselmi Fabio2; Chunhong Pan1; Tomaso Poggio2
|
| 出版日期 | 2016 |
| 会议日期 | 2016.09.25-2016.09.28 |
| 会议地点 | Phonex, Arizona, USA |
| 关键词 | Invariance Representation Down-samppling |
| 英文摘要 | Invariant representations of images can significantly reduce the sample complexity of a classifier performing object identification or categorization as shown in a recent analysis of invariant representations for object recognition. In the case of geometric transformations of images the theory [1] shows how invariant signatures can be learned in a biologically plausible way from unsupervised observations of the transformations of a set of randomly chosen template images. Here we extend the theory to non-geometric transformations such as blur and down-sampling. The proposed algorithm achieve an invariant representation via two simple biologically-plausible steps: 1. compute normalized dot products of the input with the stored transformations of each template, and 2. for each template compute the statistics of the resulting set of values such as the histogram or moments. The performance of our system on challenging blurred and low resolution face matching tasks exceeds the previous state-of-the-art by a large margin which grows with increasing image corruption. |
| 会议录 | 2016 IEEE International Conference on Image Processing, 10.1109/ICIP.2016.7533029
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/12034]  |
| 专题 | 自动化研究所_空天信息研究中心 |
| 通讯作者 | Tomaso Poggio |
| 作者单位 | 1.CASIA 2.MIT |
| 推荐引用方式 GB/T 7714 | Gu HX,Leibo Joel,Anselmi Fabio,et al. Invariant representation for blur and down-sampling transformations[C]. 见:. Phonex, Arizona, USA. 2016.09.25-2016.09.28. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。