Learning rotation invariant convolutional filters for texture classification

Diego Marcos, Michele Volpi, Devis Tuia

Research output: Chapter in Book/Report/Conference proceedingConference paperAcademicpeer-review

45 Citations (Scopus)

Abstract

We present a method for learning discriminative filters using a shallow Convolutional Neural Network (CNN). We encode rotation invariance directly in the model by tying the weights of groups of filters to several rotated versions of the canonical filter in the group. These filters can be used to extract rotation invariant features well-suited for image classification. We test this learning procedure on a texture classification benchmark, where the orientations of the training images differ from those of the test images. We obtain results comparable to the state-of-the-art. Compared to standard shallow CNNs, the proposed method obtains higher classification performance while reducing by an order of magnitude the number of parameters to be learned.

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2012-2017
Number of pages6
ISBN (Electronic)9781509048472
ISBN (Print)9781509048472
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event23rd International Conference on Pattern Recognition, ICPR 2016 - Cancun, Mexico
Duration: 4 Dec 20168 Dec 2016

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume0
ISSN (Print)1051-4651

Conference

Conference23rd International Conference on Pattern Recognition, ICPR 2016
CountryMexico
CityCancun
Period4/12/168/12/16

Fingerprint Dive into the research topics of 'Learning rotation invariant convolutional filters for texture classification'. Together they form a unique fingerprint.

Cite this