Andrearczyk, Vincent and Whelan, Paul F. ORCID: 0000-0001-9230-7656 (2016) Using filter banks in Convolutional Neural Networks for texture classification. Pattern Recognition Letters, 84 . pp. 63-69. ISSN 0167-8655
Abstract
Deep learning has established many new state of the art solutions in the last decade in areas such as object, scene and speech recognition. In particular Convolutional Neural Network (CNN) is a category of deep learning which obtains excellent results in object detection and recognition tasks. Its architecture is indeed well suited to object analysis by learning and classifying complex (deep) features that represent parts of an object or the object itself. However, some of its features are very similar to texture analysis methods. CNN layers can be thought of as filter banks of complexity increasing with the depth. Filter banks are powerful tools to extract texture features and have been widely used in texture analysis. In this paper we develop a simple network architecture named Texture CNN (T-CNN) which explores this observation. It is built on the idea that the overall shape information extracted by the fully connected layers of a classic CNN is of minor importance in texture analysis. Therefore, we pool an energy measure from the last convolution layer which we connect to a fully connected layer. We show that our approach can improve the performance of a network while greatly reducing the memory usage and computation.
Metadata
Item Type: | Article (Published) |
---|---|
Refereed: | Yes |
Uncontrolled Keywords: | computer vision; image analysis; Texture classification; Convolutional Neural Networks; dense orderless pooling; filter banks |
Subjects: | Computer Science > Image processing |
DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering |
Publisher: | Elsevier |
Official URL: | https://doi.org/10.1016/j.patrec.2016.08.016 |
Copyright Information: | © 2016 Elsevier |
Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License |
ID Code: | 22094 |
Deposited On: | 27 Oct 2017 13:32 by Paul Whelan . Last Modified 11 Jan 2019 10:31 |
Documents
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
239kB |
Metrics
Altmetric Badge
Dimensions Badge
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record