Image classification with a deep network model based on compressive sensing
Y Gan, T Zhuo, C He - 2014 12th International Conference on …, 2014 - ieeexplore.ieee.org
Y Gan, T Zhuo, C He
2014 12th International Conference on Signal Processing (ICSP), 2014•ieeexplore.ieee.orgTo simplify the parameter of the deep learning network, a cascaded compressive sensing
model “CSNet” is implemented for image classification. Firstly, we use cascaded
compressive sensing network to learn feature from the data. Secondly, CSNet generates the
feature by binary hashing and block-wise histograms. Finally, a linear SVM classifier is used
to classify these features. The experiments on the MNIST dataset indicate that higher
classification accuracy can be obtained by this algorithm.
model “CSNet” is implemented for image classification. Firstly, we use cascaded
compressive sensing network to learn feature from the data. Secondly, CSNet generates the
feature by binary hashing and block-wise histograms. Finally, a linear SVM classifier is used
to classify these features. The experiments on the MNIST dataset indicate that higher
classification accuracy can be obtained by this algorithm.
To simplify the parameter of the deep learning network, a cascaded compressive sensing model “CSNet” is implemented for image classification. Firstly, we use cascaded compressive sensing network to learn feature from the data. Secondly, CSNet generates the feature by binary hashing and block-wise histograms. Finally, a linear SVM classifier is used to classify these features. The experiments on the MNIST dataset indicate that higher classification accuracy can be obtained by this algorithm.
ieeexplore.ieee.org
Showing the best result for this search. See all results