Title
Deep neural networks for texture classification-A theoretical analysis.
Abstract
We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik–Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity.
Year
DOI
Venue
2018
10.1016/j.neunet.2017.10.001
Neural Networks
Keywords
Field
DocType
Deep neural network,Texture classification,vc dimension
VC dimension,Feature vector,Pattern recognition,Convolutional neural network,Word error rate,Feature extraction,Curse of dimensionality,Intrinsic dimension,Artificial intelligence,Artificial neural network,Machine learning,Mathematics
Journal
Volume
Issue
ISSN
97
1
0893-6080
Citations 
PageRank 
References 
8
0.51
15
Authors
7
Name
Order
Citations
PageRank
Saikat Basu1857.05
supratik mukhopadhyay226739.44
Manohar Karki3524.12
Robert DiBiano4544.79
Sangram Ganguly513620.73
Ramakrishna R. Nemani680.84
Shreekant Gayaka7182.13