基于全局优化策略的场景分类算法

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (638 KB) HTML (0 KB)
输出: BibTeX | EndNote (RIS)

摘要提出一种基于全局优化策略的场景分类算法.该算法基于整幅图像提取全局场景特征——空间包络特征.从图像块中提取视觉单词，且定义隐变量表示该视觉单词语义，然后引入隐状态结构图描述整幅图像的视觉单词上下文;在场景分类策略上，构造由相容函数组成的目标函数，其中相容函数度量全局场景特征、隐变量与场景类别标记的相容度，通过求解目标函数的全局最优解推断图像的场景类别标记.在标准场景图像库上的对比实验表明该算法优于当前有代表性的场景分类算法.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	金泰松
	李玲玲
	李翠华

关键词 ：图像解析, 场景分类, 函数优化, 视觉单词

Abstract：A scene classification algorithm based on global optimized framework is proposed. Firstly,the global scene feature named spatial envelop is obtained from the whole image,the visual word of each image block is extracted,and latent variable is defined to represent the semantic feature of the extracted visual word. Secondly,the structure graph of latent state is introduced to represent the context of visual words. In respect to scene classification strategy,objective function consisting of different potential functions is constructed in which potential functions are defined to measure the relevance of the variables including global scene feature,latent variables and scene category. Finally,the scene category of the image is determined when the global optimized solution of objective function is obtained. The experiments on the standard dataset demonstrate that the proposed algorithm achieves better results than the state-of-the-art algorithms.

Key words： Image Analysis Scene Classification Function Optimization Visual Word

收稿日期: 2012-06-13

ZTFLH:

TP391

基金资助:国家自然科学基金项目(No.41171341)、航空科学基金项目(No.20125168001)、教育部新世纪优秀人才支持计划项目(No.NCET-09-0126)、教育部博士点基金项目(No.20110121110020)、河南省科技创新人才杰出青年项目(No.114100510006)、福建省自然科学基金项目(No.2011J01365)、郑州市科技创新人才培育计划项目(No.10PTGG342-1)资助

作者简介: 金泰松(通讯作者)，男，1978年生，博士，讲师，主要研究方向为计算机视觉、遥感影像分析.E-mail:jintaisong@xmu.edu.cn.李玲玲，女，1973年生，副教授，博士后，主要研究方向为计算机视觉、图像处理.李翠华，男，1960年生，教授，博士生导师，主要研究方向为计算机视觉、模式识别.

引用本文:

金泰松，李玲玲，李翠华. 基于全局优化策略的场景分类算法[J]. 模式识别与人工智能, 2013, 26(5): 440-446. JIN Tai-Song,LI Ling-Ling,LI Cui-Hua. Scene Classification Based on Global Optimized Framework. , 2013, 26(5): 440-446.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/ 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2013/V26/I5/440

[1] Jiang Yue,Wang Runsheng,Wang Cheng. Scene Classification with Context Pyramid Features. Journal of Computer-Aided Design Computer Graphics,2010,22(8): 1366-1373 (in Chinese)
(江悦,王润生,王程.采用上下文金字塔特征的场景分类.计算机辅助设计与图形学学报,2010,22(8): 1366-1373)
[2] Wang Yushi,Gao Wen. Kernel-Based Image Classification Using the Context of Visual Words. Journal of Image and Graphics,2010,15(4): 607-616 (in Chinese)
(王宇石,高文.用基于视觉单词上下文的核函数对图像分类.中国图象图形学报,2010,15(4): 607-616)
[3]Qin Jianzhao,Yung N H C. Scene Categorization via Contextual Visual Words. Pattern Recognition,2010,43(5): 1874-1888
[4] Lazebnik S,Schmid C,Ponce J. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York,USA,2006,Ⅱ: 2169-2178
[5] Bosch A,Muoz,Zisserman A.Scene Classification Using a Hybrid Generative/Discriminative Approach. IEEE Trans on Pattern Analysis and Machine Intelligence,2008,30(4): 712-727
[6] Rasiwasia N,Vasconcelos N M. Scene Classification with Low-Dimensional Semantic Spaces and Weak Supervision // Proc of the IEEE Conference on Computer Vision and Pattern Recognition,Anchorage,USA,2008: 1-6
[7] Bosch A,Muoz X,Marti R. A Review: Which is the Best Way to Organize/Classify Images by Content? Images and Vision Computing,2007,25(6): 778-791
[8] Yang Dan,Li Bo,Zhao Hong. An Adaptive Algorithm for Robust Visual Codebook Generation and Its Natural Scene Categorization Application. Journal of Electronics Information Technology,2010,32(9): 2139-2144 (in Chinese)
(杨丹,李博,赵红.鲁棒视觉词汇本的自适应构造与自然场景分类应用.电子与信息学报,2010,32(9): 2139-2144)
[9] Jiang Y,Chen J,Wang R S. Fusing Local and Global Information for Scene Classification. Optical Engineering,2010,49(4): 1-10
[10] Song D J,Tao D C. Biologically Inspired Feature Manifold for Scene Classification. IEEE Trans on Image Processing,2010,19(1): 174-184
[11] Xiao Chunxia,Liu Shu,Lin Chengchun,et al. A Global Space-Time Optimization Framework for Video Completion. Journal of Computer-Aided Design Computer Graphics,2008,20(9): 1204-1211
(肖春霞,刘舒,林成春,等.基于时空全局优化的视频修复.计算机辅助设计与图形学学报,2008,20(9): 1204-1211)
[12] Wang Y,Mori G. A Discriminative Latent Model of Object Classes and Attributes // Proc of the 11th European Conference on Computer Vision,Crete,Greece,2010: 155-168
[13] Oliva A,Torralba A. Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope. International Journal of Computer Vision,2001,42(3): 145-175
[14] Greene M R,Oliva A. Recognition of Natural Scenes from Global Properties: Seeing the Forest without Representing the Trees. Cognitive Psychology,2009,58(2): 137-176
[15] Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision,2004,60(2): 91-110
[16] Jurie F,Triggs B. Creating Efficient Codebooks for Visual Recognition // Proc of 10th IEEE International Conference on Computer Vision,2005,Ⅰ: 604-610
[17] Li F F,Pieriro P. A Bayesian Hierarchical Model for Learning Natural Scene Categories // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego,USA,2005,Ⅱ: 524-531
[18] Felzenszwalb P F,Huttenlocher D P. Efficient Belief Propagation for Early Vision // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Washington DC,USA,2004: 261-268
[19] Felzenszwalb P F,McAllester D,Ramanan D. A Discriminatively Trained,Multiscale,Deformable Part Model // Proc of IEEE Conference on Computer Vision and Pattern Recognition. Alaska,USA,2008: 1-8
[20] Do T M T,Artières T. Large Margin Training for Hidden Markov Models with Partially Observed States // Proc of the 26th International Conference on Machine Learning. New York,USA,2009: 265- 272
[21] Bosch A,Zisserman A,Muoz A. Scene Classification via pLSA // Proc of the 9th European Conference on Computer Vision. Graz,Austria,2006: 517-530