Multi-layer feature extractions for image classification - Knowledge from deep CNNs

Kazuya Ueki, Tetsunori Kobayashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Recently, there has been considerable research into the application of deep learning to image recognition. Notably, deep convolutional neural networks (CNNs) have achieved excellent performance in a number of image classification tasks, compared with conventional methods based on techniques such as Bag-of-Features (BoF) using local descriptors. In this paper, to cultivate a better understanding of the structure of CNN, we focus on the characteristics of deep CNNs, and adapt them to SIFT+BoF-based methods to improve the classification accuracy. We introduce the multi-layer structure of CNNs into the classification pipeline of the BoF framework, and conduct experiments to confirm the effectiveness of this approach using a fine-grained visual categorization dataset. The results show that the average classification rate is improved from 52.4% to 69.8%.

Original languageEnglish
Title of host publication2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015
EditorsShahjahan Miah, Alena Uus, Panos Liatsis
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages9-12
Number of pages4
ISBN (Electronic)9781467383530
DOIs
Publication statusPublished - 2015 Oct 30
Event22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015 - London, United Kingdom
Duration: 2015 Sept 102015 Sept 12

Publication series

Name2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015

Other

Other22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015
Country/TerritoryUnited Kingdom
CityLondon
Period15/9/1015/9/12

Keywords

  • Bag-of-Features
  • Deep learning
  • Feature extraction
  • Fine-grained visual categorization
  • Generic object recognition

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Multi-layer feature extractions for image classification - Knowledge from deep CNNs'. Together they form a unique fingerprint.

Cite this