Multi-layer feature extractions for image classification — Knowledge from deep CNNs
Authors:
- 1 September 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. abs 1312 4 (21578672) , 9-12
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%.Keywords
This publication has 14 references indexed in Scilit:
- Image Classification with the Fisher Vector: Theory and PracticeInternational Journal of Computer Vision, 2013
- Leveraging category-level labels for instance-level image retrieval2012
- Automated Flower Classification over a Large Number of Classes2008
- CSIFT: A SIFT Descriptor with Color Invariant Characteristics2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Scale & Affine Invariant Interest Point DetectorsInternational Journal of Computer Vision, 2004
- Object recognition from local scale-invariant features1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Face recognition: a convolutional neural-network approachIEEE Transactions on Neural Networks, 1997