全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种基于视觉注意模型的图像分类方法

DOI: 10.11834/jig.20081017

Keywords: 视觉系统视觉注意稀少性图像分类

Full-Text   Cite this paper   Add to My Lib

Abstract:

视觉选择性注意机制是人类视觉系统的重要组成部分。近年来的研究表明,自下而上的视觉选择性注意模型在物体识别等方面得到了良好的应用。但是,视觉选择性注意模型在描述图像内容时存在着明显的不足,一个显著的特征在某些情况下可能不会得到注意,人眼更可能会注意到一幅图像里比较稀少的特征。针对上述情况,提出了一种基于视觉选择性注意模型和全局稀少性相结合的视觉注意模型进行图像分类。实验结果表明,该方法在多类物体分类中达到97?74%的总准确率,取到了非常好的效果。

References

[1]  Itti L, Koch C. Computational modeling of visual attention [J]. Nature Reviews Neuroscience, 2001, 2 (3) : 194 - 203.
[2]  Frintrop S. VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search [D]. Bown, Germany : University of Bonn, 2005.
[3]  Mancas M, Gosselin B, Macq B. A rarity-based visual attention mapapplication to texture description [ A ]. In: Proceedings of IEEE International Conference on Image Processing [C], Atlanta, USA, 2006 : 445 - 448.
[4]  Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20( 11 ) : 1254 - 1259.
[5]  Fergus R, Perona P, Zisserman A. A sparse object category model for efficient learning and exhaustive recognition[ A]. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition [C] , San Diego, CA, USA, 2005:380 -387.
[6]  Opelt A, Pinz A. Object localization with boosting and weak supervision for generic object recognition[ A]. In: Proceedings of the 14th Scandinavian Conference on Image Analysis [C] , Joensuu, Finland, 2005 : 862 - 871.
[7]  Opelt A, Pinz A, Fussenegger M. Generic object recognition with boosting [J]. Pattern Analysis and Machine Intelligence, 2006, 28(3): 416 -431.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133