Improved image classification using topological persistence
Pages 161 - 168
Abstract
Image classification has been a topic of interest for many years. With the advent of Deep Learning, impressive progress has been made on the task, resulting in quite accurate classification. Our work focuses on improving modern image classification techniques by considering topological features as well. We show that incorporating this information allows our models to improve the accuracy, precision and recall on test data, thus providing evidence that topological signatures can be leveraged for enhancing some of the state-of-the art applications in computer vision.
References
[1]
{AC09} Adams H., Carlsson G.: On the nonlinear statistics of range image patches. SIAM Journal on Imaging Sciences 2, 1 (2009), 110--117. 4
[2]
{BEK10} Bendich P., Edelsbrunner H., Kerber M.: Computing robustness and persistence for images. IEEE Transactions on Visualization and Computer Graphics 16, 6 (Nov 2010), 1251--1260. 1
[3]
{BKRW17} Bauer U., Kerber M., Reininghaus J., Wagner H.: Phat - persistent homology algorithms toolbox. J. Symb. Comput. 78, C (Jan. 2017), 76--90. 1
[4]
{Bub15} Bubenik P.: Statistical topological data analysis using persistence landscapes. Journal of Machine Learning Research 16, 1 (2015), 77--102. 4
[5]
{CBK09} Chung M., Bubenik P., Kim P.: Persistence diagrams of cortical surface data. In Information processing in medical imaging (2009), Springer, pp. 386--397. 1
[6]
{DDJ*14} Deng J., Ding N., Jia Y., Frome A., Murphy K., Bengio S., Li Y., Neven H., Adam H.: Large-Scale Object Classification Using Label Relation Graphs. Springer International Publishing, 2014, pp. 48--64. 2
[7]
{DDS*09} Deng J., Dong W., Socher R., Li L.-J., Li K., Fei-Fei L.: ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09 (2009), vol. 115, pp. 211--252. 1
[8]
{DFW12} Dey T. K., Fan F., Wang Y.: Computing topological persistence for simplicial maps. CoRR abs/1208.5018 (2012). 3, 7
[9]
{DFW13} Dey T. K., Fan F., Wang Y.: Graph induced complex on point data. In Proceedings of the Twenty-ninth Annual Symposium on Computational Geometry (New York, NY, USA, 2013), SoCG '13, ACM, pp. 107--116. 3, 7
[10]
{DL13} Dirafzoon A., Lobaton E.: Topological mapping of unknown environments using an unlocalized robotic swarm. In 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (Nov 2013), pp. 5545--5551. 1
[11]
{DSG07} De Silva V., Ghrist R.: Coverage in sensor networks via persistent homology. Algebraic & Geometric Topology 7, 1 (2007), 339--358. 1
[12]
{DSW16} Dey T. K., Shi D., Wang Y.: Simba: An efficient tool for approximating rips-filtration persistence via simplicial batch-collapse. In European Symposium on Algorithms (2016), vol. 57. 1, 3
[13]
{ELZ02} Edelsbrunner H., Letscher D., Zomorodian A.: Topological persistence and simplification. Discrete Comput. Geom. 28, 4 (Nov. 2002), 511--533. 2
[14]
{GCB04} Gabriella Csurka Christopher R. Dance L. F. J. W., Bray C.: Visual categorization with bags of keypoints. ECCV SLCV Workshop (2004), 1--22. 2
[15]
{GHP06} Griffin G., Holub A., Perona P.: Caltech-256 object category dataset. 6
[16]
{GM05} Ghrist R., Muhammad A.: Coverage and hole-detection in sensor networks via homology. In IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005. (April 2005), pp. 254--260. 1
[17]
{GWK*15} Gu J., Wang Z., Kuen J., Ma L., Shahroudy A., Shuai B., Liu T., Wang X., Wang G.: Recent advances in convolutional neural networks. CoRR abs/1512.07108 (2015). 2
[18]
{HH10} Herbert E., Harer J.: Computational topology: an introduction. 1, 2, 3
[19]
{HPR*14} Harvey W., Park I.-H., Rãijbel O., Pascucci V., Bremer P.-T., Li C., Wang Y.: A collaborative visual analytics suite for protein folding research. Journal of Molecular Graphics and Modelling 53 (2014), 59 -- 71. 4
[20]
{KHN*15} Kwitt R., Huber S., Niethammer M., Lin W., Bauer U.: Statistical topological data analysis - a kernel perspective. In Advances in Neural Information Processing Systems 28, Cortes C., Lawrence N. D., Lee D. D., Sugiyama M., Garnett R., (Eds.). Curran Associates, Inc., 2015, pp. 3070--3078. 4
[21]
{Kob14} Kobayashi T.: Dirichlet-based histogram feature transform for image classification. In CVPR14 (June 2014), pp. 3278--3285. 1
[22]
{Koh96} Kohavi R.: Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (1996), KDD'96, AAAI Press, pp. 202--207. 4
[23]
{KSH12} Krizhevsky A., Sutskever I., Hinton G. E.: Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (2012), pp. 1097--1105. 2, 7
[24]
{Kur15} Kurlin V.: A fast persistence-based segmentation of noisy 2D clouds with provable guarantees. 3--12. 1
[25]
{LBBH98} LeCun Y., Bottou L., Bengio Y., Haffner. P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 11 (November 1998), 2278--2324. 6
[26]
{Low99} Lowe D. G.: Object recognition from local scale-invariant features. In Proceedings of the Seventh IEEE International Conference on Computer Vision (1999), vol. 2, pp. 1150--1157 vol.2. 2, 5
[27]
{Low09} Lowe D.: Learning Multiple Layers of Features from Tiny Images. P, April 2009. 5
[28]
{LSP*12} Li S., Simons L., Pakaravoor J. B., Abbasinejad F., Owens J. D., Amenta N.: kann on the gpu with shifted sorting. In Proceedings of the Fourth ACM SIGGRAPH / Eurographics Conference on High-Performance Graphics (Aire-la-Ville, Switzerland, Switzerland, 2012), EGGH-HPG'12, Eurographics Association, pp. 39--47. 3
[29]
{MS02} Mikolajczyk K., Schmid C.: An affine invariant interest point detector. 5
[30]
{Mun84} Munkres J. R.: Elements of Algebraic Topology, 1 ed. Perseus, Cambridge, Massachusetts, 1984, ch. 1. 3
[31]
{OVS13} Oneata D., Verbeek J., Schmid C.: Action and event recognition with fisher vectors on a compact feature set. 1817--1824. 2
[32]
{PL15} Perronnin F., Larlus D.: Fisher vectors meet neural networks: A hybrid classification architecture. pp. 3743--3752. 1
[33]
{PSM10} Perronnin F., Sanchez J., Mensink T.: Improving the Fisher Kernel for Large-Scale Image Classification. Springer Berlin Heidelberg, Berlin, Heidelberg, September 2010, pp. 143--156. 1
[34]
{SB98} Sutton R. S., Barto A.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge, Massachusetts, 1998. 6
[35]
{SPMV13} Sanchez J., Perronnin F., Mensink T., Verbeek J.: Image classification with the fisher vector: Theory and practice. International Journal of Computer Vision, Springer (May 2013), 222--245. 1, 2, 5
[36]
{SVZ13} Simonyan K., Vedaldi A., Zisserman A.: Deep fisher networks for large-scale image classification. In Advances in Neural Information Processing Systems 26, Burges C. J. C., Bottou L., Welling M., Ghahramani Z., Weinberger K. Q., (Eds.). Curran Associates, Inc., 2013, pp. 163--171. 1
[37]
{The15} The GUDHI Project: GUDHI User and Reference Manual. GUDHI Editorial Board, 2015. 1
[38]
{TMB14} Turner K., Mukherjee S., Boyer D. M.: Persistent homology transform for modeling shapes and surfaces. Information and Inference (2014), iau011. 1
[39]
{vdMH08} van der Maaten L., Hinton G.: Visualizing data using t-SNE, November 2008. 4
[40]
{WYY*10} Wang J., Yang J., Yu K., Lv F., Huang T., Gong Y.: Locality-constrained linear coding for image classification. In CVPR10 (June 2010), pp. 3360--3367. 2
[41]
{YYGH09} Yang J., Yu K., Gong Y., Huang T.: Linear spatial pyramid matching using sparse coding for image classification. In CVPR09 (June 2009), pp. 1794--1801. 2
Recommendations
An image classification approach for painting using improved convolutional neural algorithm
AbstractThe widespread availability of digitized fine art collections in museums and galleries has generated a demand for efficient software tools. These tools enable rapid retrieval and semantic classification of art images. Traditional image ...
Improved classification with allocation method and multiple classifiers
We propose a new allocation method for building a classification ensemble.Allocation method uses multiple classifiers: the allocator and micro classifiers.Allocator separates the dataset and allocates them to one of micro classifiers.Allocator is based ...
Improved image representation and sparse representation for image classification
AbstractIt seems that for multiple available images of the same object, the pixel values at the same image position are almost always different, which is especially obvious for the deformable object. This implies that it will be not easy to correctly ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2017
175 pages
ISBN:9783038680499
- Conference Chairs:
- Matthias Hullin,
- Reinhard Klein,
- Thomas Schultz,
- Angela Yao
Publisher
Eurographics Association
Goslar, Germany
Publication History
Published: 25 September 2017
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Jan 2025