ABSTRACT
The convolution neural network has proved to be an efficient method for the image processing. It can optimize the convolution of the convolutional neural network and the filter in the poolinglayer Function, and optimize the performance of the role, and the number of parameters. It can construct a certain structure of the convolution neural network, and then the image data set is classified and processed to obtain the image model of the desired classification result.
- Kodovsky J, Fridrich J, Holub V. Ensemble classifiers for steganalysis of digital media [J]. IEEE Trans on Information Forensics & Security, 2012, 7(2): 432-444Google ScholarDigital Library
- IEEE Transactions on Pattern Analysis & Machine Intelligence.2012, 35(11):2765-2781.Google Scholar
- Peng X, Zhang L, Yi Z.Scalable Sparse Subspace Clustering. ComputerVision and Pattern Recognition. IEEE, 2013:430-437Google Scholar
- Xu J, Xu K, Chen K, Reweighted sparse subspace clustering. Computer Vision &Image Understanding.2015:25-37.Google Scholar
- Patel V M, Nguyen H V, Vidal R. Latent Space Sparse and Low-Rank Subspace Clustering. IEEE Journal of Selected Topics in Signal Processing. 2015, 9(4):691-701.Google Scholar
- Sainath T N, Mohamed A R, Kingsbury B, Deep convolutional neuralnetworks for LVCSR [C] Proc of IEEE International Conference nAcoustics, Speech and Signal Processing. 2013: 8614-8618.Google Scholar
- Pevný T, Bas P, Fridrich J. Steganalysis by subtractive pixel adjacency.Google Scholar
- matrix [J]. IEEE Trans on Information Forensics & Security, 2010, 5 (2): 215-224Google ScholarDigital Library
Recommendations
Scene text recognition using residual convolutional recurrent neural network
Text is a significant tool for human communication, and text recognition in scene images becomes more and more important. In this paper, we propose a residual convolutional recurrent neural network for solving the task of scene text recognition. The ...
Convolutional Recurrent Neural Networks for Text Classification
Recurrent neural network (RNN) and convolutional neural network (CNN) are two prevailing architectures used in text classification. Traditional approaches combine the strengths of these two networks by straightly streamlining them or linking features ...
Maxout neurons for deep convolutional and LSTM neural networks in speech recognition
We combine maxout neurons with convolutional and LSTM structures for DNNs.The optimal network structures and training strategies are explored for the models.Experiments are carried out for 6 languages on the IARPA Babel data sets.State-of-the-art ...
Comments