基于GBVS改进的Object Bank场景分类方法

doi:10.3969/j.issn.1006-2475.2017.01.012

计算机与现代化 ›› 2017, Vol. 0 ›› Issue (1): 61-64+70.doi: 10.3969/j.issn.1006-2475.2017.01.012

基于GBVS改进的Object Bank场景分类方法

(1.同济大学电子与信息工程学院计算机系，上海 201804; 2.福州大学物理与信息工程学院，福建福州 350116)

收稿日期:2016-06-16 出版日期:2017-01-12 发布日期:2017-01-11
作者简介:陈梦婷(1992-)，女，浙江温州人，同济大学电子与信息工程学院计算机系硕士研究生，研究方向：图像处理，场景分类; 陈思喜(1975-)，男，福建福鼎人，福州大学物理与信息工程学院讲师，硕士，研究方向：数字媒体，虚拟互动。

New Object Bank Method for Scene Classification Based on GBVS

(1. Department of Computer Science, College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China;
2. College of Physics and Information Engineering, Fuzhou University, Fuzhou 350116, China)

Received:2016-06-16 Online:2017-01-12 Published:2017-01-11

摘要/Abstract

摘要： Object Bank (OB)是一种基于物体的高层语义图像特征表示，该方法所提取的高层特征具有较丰富的场景语义。然而，该方法所采用的物体检测器检测物体的准确率并不高，从而影响高层特征的提取效果。针对OB方法中物体检测器准确率较低的缺点，提出一种基于Graph-Based Visual Saliency (GBVS)显著性分析算法改进的OB方法。先通过GBVS方法对图像进行显著性处理，计算图像中的显著性区域，然后结合OB方法中的物体检测器对显著区域进行检测，提取更具有场景语义的高层特征。实验结果表明，该方法突出了具有显著性的物体，提高了OB方法中目标检测器的准确率，在OB方法的基础上提取出了更具有显著性的图像特征OB方法提高了4%。，并在分类准确率上比

关键词: object bank, GBVS, 场景分类, 视觉显著性, 高层特征

Abstract: Object bank (OB) representation is a novel image representation for high-level visual tasks, which encodes semantic and spatial information of the objects within an image. However, the poor precision of the object detectors in OB method influences the extraction effect of high-level image feature. In order to solve this problem, a new OB method improved by Graph-Based Visual Saliency (GBVS) is proposed. Firstly, GBVS saliency model is utilized to process the image and detect the saliency regions and extract better high-level feature. The experiments results show that the proposed method performs better in classification and increases the classification accuracy of 4%.

Key words: object bank, GBVS, scene classification, visual saliency, high-level feature

中图分类号:

TP751

陈梦婷1，陈思喜2. 基于GBVS改进的Object Bank场景分类方法[J]. 计算机与现代化, 2017, 0(1): 61-64+70.

CHEN Meng-ting1, CHEN Si-xi2. New Object Bank Method for Scene Classification Based on GBVS[J]. Computer and Modernization, 2017, 0(1): 61-64+70.

参考文献

[1] 冯炜. 图像场景分类的关键技术研究[D]. 北京:北京交通大学, 2008.

[2] 李学龙,史建华,董永生,等. 场景图像分类技术综述[J]. 中国科学:信息科学, 2015,45(7):827-848.

[3] Li Li-jia, Su Hao, Lim Y, et al. Object bank: An object-level image representation for high-level visual recognition[J]. International Journal of Computer Vision, 2014,107(1):20-39.

[4] Li Li-jia, Su Hao, Lim Y, et al. Objects as attributes for scene classification[C]// Proceedings of the 11th European Conference on Trends and Topics in Computer Vision. 2010:57-69.

[5] Harel J, Koch C, Perona P. Graph-based visual saliency[C]// Proceedings of the 2006 Advances in Neural Information Processing Systems. 2006:545-552.

[6] Li Li-jia, Su Hao, Xing E P, et al. Object bank: A high-level image representation for scene classification & semantic feature sparsification[C]// Proceedings of the 2010 Advances in Neural Information Processing Systems. 2010:719-729.

[7] Zipf G K. Selected studies of the principle of relative frequency in language[J]. Language, 1932,9(1):89-92.

[8] Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2010,32(9):1627-1645.

[9] Felzenszwalb P F, McAllester D, Ramanan D. A discriminatively trained, multiscale, deformable part model[C]// Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. 2008.

[10] Mesnil G, Rifai S, Bordes A, et al. Unsupervised and transfer learning under uncertainty: From object detections to scene categorization[C]// Proceedings of the 2013 International Conference on Pattern Recognition Applications and Methods. 2013:345-354.

[11] Koch K, McLean J, Segev R, et al. How much the eye tells the brain[J]. Current Biology CB, 2006,16(14):1428-1434.

[12] Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection[C]// Proceedings of the 2009 IEEE International Conference on Computer Vision and Pattern Recognition. 2009:1597-1604.

[13] Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1998,20(11):1254-1259.

[14] Achanta R, Estrada F, Wils P, et al. Salient region detection and segmentation[C]// Proceedings of the 6th International Conference on Computer Vision Systems. 2008:66-75.

[15] Hou Xiaodi, Zhang Liqing. Saliency detection: A spectral residual approach[C]// Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. 2007.

[16] Chang Chin-Chung, Lin Chin-Jen. LIBSVM: A Library for Support Vector Machines[EB/OL]. http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2012-11-10.

[17] Li Li-jia, Li Fei-fei. What, where and who? Classifying event by scene and object recognition[C]// Proceedings of the 11th IEEE International Conference on Computer Vision. 2007.

[18] Li Fei-fei, Perona P. A Bayesian hierarchical model for learning natural scene categories[C]// Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision & Pattern Recognition. 2005,2:524-531.

[19] Quattoni A, Torralba A. Recognizing indoor scenes[C]// Proceedings of the 2009 IEEE Conference on Computer Vision & Pattern Recognition. 2009:413-420.

基于GBVS改进的Object Bank场景分类方法

New Object Bank Method for Scene Classification Based on GBVS

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	刘宝宝, 杨菁菁, 陶露, 王贺应. 基于注意力的DSMSC的遥感图像场景分类[J]. 计算机与现代化, 2024, 0(12): 72-77.
[2]	朱原冶, 倪建军, 唐广翼. 一种基于改进卷积神经网络的RGB-D室内场景分类方法[J]. 计算机与现代化, 2023, 0(04): 73-77.
[3]	陶陈;徐丹;张海玉;邓健. 基于视觉显著性和对称投影的禁止路标检测算法[J]. 计算机与现代化, 2013, 1(2): 35-37+4.