ABSTRACT
With the development of artificial intelligence, classification tasks become more and more popular, but the amount of data is growing dramatically. There are mainly two ways to deal with this problem, one is to reduce the data dimensions directly, the other one is to take advantage of all data through deep learning. In this paper, we will compare these two data processing methods. The first way is to reduce the extracted features' dimensions through manifold learning and then feed into classifiers, and the other way is to deal it directly with deep learning. The experimental results show that deep learning has a better ability than manifold learning in the classification task.
- Permuter H, Francos J, Jermyn I. 2006. A study of Gaussian mixture models of color and texture features for image classification and segmentation. Pattern Recognition,39(4): 695--706. Google ScholarDigital Library
- Žunić J, Hirota K, Rosin P L. 2010. Hu moment invariant as a shape circularity measure. Pattern Recognition, 43(1): 47--57. Google ScholarDigital Library
- Banerji S, Sinha A, Liu C. 2013.New image descriptors based on color, texture, shape, and wavelets for object and scene image classification. Neurocomputing, 117: 173--185.Google ScholarCross Ref
- Ramya K. Raman and C. Chandra Sekhar. 2014. Concept Level Discriminant Analysis Techniques for Dimension Reduction in Image Classification Tasks. In Proceedings of the 2014 Indian Conference on Computer Vision Graphics and Image Processing (ICVGIP '14). ACM, New York, NY, USA, Article 44, 8 pages. Google ScholarDigital Library
- Xiumei Wang, Weifang Liu, Jie Li, and Xinbo Gao. 2016. A novel dimensionality reduction method with discriminative generalized eigen-decomposition. Neurocomput. 173, P2 (January 2016), 163--171. Google ScholarDigital Library
- Krizhevsky A, Sutskever I, Hinton G E. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 1097--1105. Google ScholarDigital Library
- Chen Y, Crawford M M, Ghosh J. 2005. Applying nonlinear manifold learning to hyperspectral data for land cover classification. Geoscience and Remote Sensing Symposium, 2005. IGARSS'05. Proceedings. 2005 IEEE International. IEEE, 6: 4311--4314.Google Scholar
- Ma L, Crawford M M, Tian J. 2010.Local manifold learning-based k-nearest-neighbor for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 48(11): 4099--4109.Google Scholar
- Tang B, Song T, Li F, et al. 2014. Fault diagnosis for a wind turbine transmission system based on manifold learning and Shannon wavelet support vector machine. Renewable Energy, 62: 1--9.Google ScholarCross Ref
- LeCun Y, Bottou L, Bengio Y, et al. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278--2324.Google ScholarCross Ref
- Ciregan D, Meier U, Schmidhuber J. 2012. Multi-column deep neural networks for image classification. Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 3642--3649. Google ScholarDigital Library
- Johnson J, Karpathy A, Fei-Fei L. 2016. Densecap: Fully convolutional localization networks for dense captioning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4565--4574.Google ScholarCross Ref
- Simonyan K, Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.Google Scholar
- Szegedy C, Liu W, Jia Y, et al. 2015. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition. 1--9.Google Scholar
- Londhe R, Pawar V. 2012. Facial expression recognition based on affine moment invariants. International Journal of Computer Science Issues(IJCSI), 9(6).Google Scholar
- Wang Y, Wang X, Zhang B, et al. 2013. A novel form of affine moment invariants of grayscale images. Elektronika ir Elektrotechnika, 19(1): 77--82.Google Scholar
- Soh L K, Tsatsoulis C. 1999. Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Transactions on geoscience and remote sensing, 37(2): 780--795.Google ScholarCross Ref
- Lowe D G. 1999. Object recognition from local scale-invariant features. Computer vision. The proceedings of the seventh IEEE international conference on. Ieee, 1999, 2: 1150--1157. Google ScholarDigital Library
- Zhu X, Ma C, Liu B, et al. 2012. Target classification using SIFT sequence scale invariants. Journal of Systems Engineering and Electronics, 23(5): 633--639.Google ScholarCross Ref
- Schölkopf B, Smola A, Müller K R. 1997. Kernel principal component analysis. International Conference on Artificial Neural Networks. Springer, Berlin, Heidelberg, 583--588. Google ScholarDigital Library
- Kim K I, Jung K, Kim H J. 2002. Face recognition using kernel principal component analysis. IEEE signal processing letters, 9(2): 40--42.Google Scholar
- Young F W. 2013. Multidimensional scaling: History, theory, and applications. Psychology Press.Google Scholar
- Mao K Z, Tan K C, Ser W. 2000. Probabilistic neural-network structure determination for pattern classification. IEEE Transactions on neural networks, 11(4): 1009--1016. Google ScholarDigital Library
- Weston J. 2014. Support Vector Machine. Tutorial, http://www.cs.columbia.edu/~kathy/cs4701/documents/jason_svm_tutorial.pdf, accessed, 10(0):0.5.Google Scholar
- Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional Architecture for Fast Feature Embedding. In Proceedings of the 22nd ACM international conference on Multimedia (MM '14). ACM, New York, NY, USA, 675--678. Google ScholarDigital Library
Index Terms
- Comparison of Manifold Learning and Deep Learning on Target Classification
Recommendations
Riemannian Manifold Learning
Recently, manifold learning has been widely exploited in pattern recognition, data analysis, and machine learning. This paper presents a novel framework, called Riemannian manifold learning (RML), based on the assumption that the input high-dimensional ...
Multi-manifold LLE learning in pattern recognition
This paper introduces Multiple Manifold Locally Linear Embedding (MM-LLE) learning. This method learns multiple manifolds corresponding to multiple classes in a data set. The proposed approach to manifold learning includes a supervised form of ...
Image classification with manifold learning for out-of-sample data
The successful applications of manifold learning in computer vision and multimedia research show that the geodesic distance along the manifold is more meaningful than Euclidean distance in the linear space. Therefore, in order to get better performance ...
Comments