| Object class recognition based on compressive sensing with sparse features inspired by hierarchical model in visual cortex | |
| Lu, Pei1,2,3; Xu, Zhiyong1; Yu, Huapeng1,3; Chang, Yongxin1,3; Fu, Chengyu1; Shao, Jianxin4; Lu, P. (lupei0@126.com) | |
| Volume | 8558 |
| Pages | 85581X |
| 2012 | |
| Language | 英语 |
| ISSN | 0277786X |
| DOI | 10.1117/12.999501 |
| Indexed By | Ei |
| Subtype | 会议论文 |
| Abstract | According to models of object recognition in cortex, the brain uses a hierarchical approach in which simple, low-level features having high position and scale specificity are pooled and combined into more complex, higher-level features having greater location invariance. At higher levels, spatial structure becomes implicitly encoded into the features themselves, which may overlap, while explicit spatial information is coded more coarsely. In this paper, the importance of sparsity and localized patch features in a hierarchical model inspired by visual cortex is investigated. As in the model of Serre, Wolf, and Poggio, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. In order to improve generalization performance, the sparsity is proposed and data dimension is reduced by means of compressive sensing theory and sparse representation algorithm. Similarly, within computational neuroscience, adding the sparsity on the number of feature inputs and feature selection is critical for learning biologically model from the statistics of natural images. Then, a redundancy dictionary of patch-based features that could distinguish object class from other categories is designed and then object recognition is implemented by the process of iterative optimization. The method is test on the UIUC car database. The success of this approach suggests a proof for the object class recognition in visual cortex. © Copyright SPIE.; According to models of object recognition in cortex, the brain uses a hierarchical approach in which simple, low-level features having high position and scale specificity are pooled and combined into more complex, higher-level features having greater location invariance. At higher levels, spatial structure becomes implicitly encoded into the features themselves, which may overlap, while explicit spatial information is coded more coarsely. In this paper, the importance of sparsity and localized patch features in a hierarchical model inspired by visual cortex is investigated. As in the model of Serre, Wolf, and Poggio, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. In order to improve generalization performance, the sparsity is proposed and data dimension is reduced by means of compressive sensing theory and sparse representation algorithm. Similarly, within computational neuroscience, adding the sparsity on the number of feature inputs and feature selection is critical for learning biologically model from the statistics of natural images. Then, a redundancy dictionary of patch-based features that could distinguish object class from other categories is designed and then object recognition is implemented by the process of iterative optimization. The method is test on the UIUC car database. The success of this approach suggests a proof for the object class recognition in visual cortex. © Copyright SPIE. |
| Conference Name | Proceedings of SPIE: Optoelectronic Imaging and Multimedia Technology II |
| Conference Date | 2012 |
| Citation statistics | |
| Document Type | 会议论文 |
| Identifier | http://ir.ioe.ac.cn/handle/181551/7696 |
| Collection | 光电探测与信号处理研究室（五室） |
| Corresponding Author | Lu, P. (lupei0@126.com) |
| Affiliation | 1. Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu 610209, China 2. College of Information Science and Technology, Shihezi University, Shihezi 832000, China 3. Graduate University, Chinese Academy of Sciences, Beijing 100049, China 4. Normal College, Shihezi University, Shihezi 832000, China |
| Recommended Citation GB/T 7714 | Lu, Pei,Xu, Zhiyong,Yu, Huapeng,et al. Object class recognition based on compressive sensing with sparse features inspired by hierarchical model in visual cortex[C],2012:85581X. |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| 2012-2170.pdf（341KB） | 会议论文 | 开放获取 | CC BY-NC-SA | Application Full Text | ||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment