基于部位特征和全局特征的物体细粒度识别

doi:10.3969/j.issn.1006-2475.2017.10.001

计算机与现代化

• 图像处理 • 下一篇

基于部位特征和全局特征的物体细粒度识别

江西师范大学计算机信息工程学院，江西南昌330022

收稿日期:2017-03-13 出版日期:2017-10-30 发布日期:2017-10-31
作者简介:陈淑娴（1991-），女，广东广州人，江西师范大学计算机信息工程学院硕士研究生，研究方向：图像处理。
基金资助:
国家自然科学基金资助项目（61662034）; 江西省教育厅科学基金一般项目（GJJ150353）

Fine-grained Object Recognition Based on Part and Global Features

江西师范大学计算机信息工程学院

College of Computer and Information Engineering, Jiangxi Normal University, Nanchang 330022, China

Received:2017-03-13 Online:2017-10-30 Published:2017-10-31

摘要/Abstract

摘要： 目前大部分细粒度识别通常仅对整体特征进行提取并分类，而忽略了角度和姿态引起的部件上视觉差异，为此提出一种基于部位特征和全局特征的物体细粒度识别方法。首先将目标进行姿态聚类，使得相同姿态下展现目标相一致的可见部位，进而提取目标的部位特征，并在各姿态类内结合目标的整体特征做分类。该模型在姿态和视角影响尤其明显的鸟类数据库CUB_200-2011上进行了实验验证，结果表明与现有的同类方法相比，本文方法具有更好的性能。

关键词: 细粒度, 姿态聚类, 部位特征, 整体特征

Abstract: Most fine-grained recognition only extracts global feature to classify and ignores visual differences of parts caused by attitude angle and pose. So this paper proposes a fine-grained recognition method by combining part feature with global feature. First, the paper does the target pose clustering to show the same visible part of object in the same pose, then extracts parts feature of object and combines global feature to classify in every pose. The proposed model is validated by the experimental results on the bird database CUB_200-2011, which has a significant effect on attitude and visual angle. The results show that the proposed method has better performance than the existing methods.

Key words: fine-grained； pose clustering, part feature, global feature

陈淑娴，刘建明. 基于部位特征和全局特征的物体细粒度识别[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2017.10.001.

CHEN Shu-xian, LIU Jian-ming. Fine-grained Object Recognition Based on Part and Global Features[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2017.10.001.

参考文献

［1］ Berg T, Liu Jiangxin, Lee S W, et al. Birdsnap: Large-scale fine-grained visual categorization of birds［C］// 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2014:2019-2026. 

［2］ Lin Yuanqing, Zhu Shenghuo, Angelova A. Image segmentation for large-scale subcategory flower recognition［C］// 2013 IEEE Workshop on Applications of Computer Vision (WACV). IEEE Computer Society, 2013:39-45.

［3］ Rodner E, Simon M, Brehm G, et al. Fine-grained recognition datasets for biodiversity analysis［J］. arXiv Preprint arXiv:1507.00913,2015.

［4］ Goering C, Rodner E, Freytag A, et al. Nonparametric part transfer for fine-grained recognition［C］// 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2014:2489-2496.

［5］ Wah C, Branson S， Welinder P, et al. The Caltech-UCSD Birds-200-2011 Dataset［DB/OL］. http://authors.library.caltech.edu/27452/1/CUB_200_2011.pdf, 2011-07-01. 

［6］ Zhang Ning, Donahue J, Girshick R, et al. Part-based R-CNNs for fine-grained category detection［J］. Lecture Notes in Computer Science, 2014, 8689:834-849.

［7］ Xiao Tianjun, Xu Yichong, Yang Kuiyuan, et al. The application of two-level attention models in deep convolutional neural network for finegrained image classification［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015:842-850.

［8］ Krause J, Gebru T， Deng Jia, et al. Learning Features and Parts for Fine-Grained Recognition［C］// 2014 22nd International Conference on Pattern Recognition (ICPR). 2014:26-33.

［9］ Simon M, Rodner E, Denzler J. Part Localization by Exploiting Deep Convolutional Networks［DB/OL］. https://filebox.ece.vt.edu/~parikh/PnA2014/posters/Posters/SimonPnA2014.pdf, 2017-03-13.

［10］Simon M, Rodner E, Denzler J. Part detector discovery in deep convolutional neural networks［C］// Asian Conference on Computer Vision(ACCV 2014). 2014:162-177.

［11］Galleguillos C, Belongie S. Context based object categorization: A critical survey［J］. Computer Vision & Image Understanding, 2010,114(6):712-722.

［12］Berg T, Belhumeur P N. POOF: Part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation［C］// 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR2013). 2013:955-962.

［13］Singh S, Gupta A, Efros A A. Unsupervised discovery of mid-level discriminative patches［C］// Proceedings of the 12th European Conference on Computer Vision(ECCV 2012). 2012:73-86.

［14］Freytag A, Rodner E， Darrell T, et al. Exemplar-specific patch features for fine-grained recognition［C］// German Conference on Pattern Recognition. 2014:144-156.

［15］Krause J, Jin Hailin, Yang Jianchao, et al. Fine-grained recognition without part annotations［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015:5546-5555.

［16］ Deng Jia, Krause J, Li Feifei. Fine-grained crowdsourcing for fine-grained recognition［C］// IEEE Conference on Computer Vision & Pattern Recognition. 2013:580-587.

［17］Darrell T, Huang Chang, Jia Yangqing. Beyond spatial pyramids: Receptive field learning for pooled image features［C］// IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2012:3370-3377.

［18］Bo Liefeng, Ren Xiaofeng, Fox D. Kernel descriptors for visual recognition［C］// Advances in Neural Information Processing Systems. 2010:1-9.

［19］Dalal N, Triggs B. Histograms of oriented gradients for human detection［C］// IEEE Computer Society Conference on Computer Vision & Pattern Recognition. 2005:886-893.

［20］Ojala T, Pietikainen M, Harwood D. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions［C］// IAPR International Conference on Pattern Recognition. 1994:582-585.

［21］Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002,24(7):971-987.

［22］Smith A R. Color gamut transform pairs［J］. ACM SIGGRAPH Computer Graphics, 1978,12(3):12-19.

［23］ 加利福尼亚理工学院. CUB-200-2011［DB/OL］. http://www.doc88.com/p-9921674941119.html, 2017-03-17.

[1]	杨贞, 单孟姣, 殷志坚, 杨凡, 李翠梅. 细粒度图像分类的通道自适应判别性学习方法[J]. 计算机与现代化, 2022, 0(10): 68-74.
[2]	周晨轶，冯宇，徐亦白，卢杉. 基于增强多重注意力机制的深度神经网络的细粒度检测[J]. 计算机与现代化, 2019, 0(09): 83-.
[3]	刘赛1,聂庆节1,刘军1,李东民2,李静2. 基于量化行为的实时数据库备份系统访问控制模型[J]. 计算机与现代化, 2018, 0(01): 116-122.
[4]	宋万里1，2，吴炜峰1. 基于改进的RBAC模型的系统用户权限控制研究[J]. 计算机与现代化, 2014, 0(9): 49-54.

基于部位特征和全局特征的物体细粒度识别

Fine-grained Object Recognition Based on Part and Global Features

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价