TY - GEN
T1 - Multi-layer feature extractions for image classification - Knowledge from deep CNNs
AU - Ueki, Kazuya
AU - Kobayashi, Tetsunori
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/10/30
Y1 - 2015/10/30
N2 - 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%.
AB - 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%.
KW - Bag-of-Features
KW - Deep learning
KW - Feature extraction
KW - Fine-grained visual categorization
KW - Generic object recognition
UR - http://www.scopus.com/inward/record.url?scp=84961757506&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84961757506&partnerID=8YFLogxK
U2 - 10.1109/IWSSIP.2015.7313924
DO - 10.1109/IWSSIP.2015.7313924
M3 - Conference contribution
AN - SCOPUS:84961757506
T3 - 2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015
SP - 9
EP - 12
BT - 2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015
A2 - Miah, Shahjahan
A2 - Uus, Alena
A2 - Liatsis, Panos
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015
Y2 - 10 September 2015 through 12 September 2015
ER -