Generic image recognition techniques are widely studied for automatic image indexing. However, many of these methods are computationally too heavy for a practically large setup. Thus, for realizing scalability, it is important to properly balance the trade-off between performance and computational cost. In recent years, methods based on a bag-of-keypoints approach have been successful and widely used. However, the preprocessing cost for building visual words becomes immense in large-scale datasets. On the other hand, methods based on global image features have been used for a long time. Because global image features can be extracted rapidly, it is relatively easy to use them with large datasets. However, the performance of global feature methods is usually poor compared to the bag-of-keypoints methods. This paper proposes a simple but powerful scheme of boosting the performance of global image features by densely sampling low-level statistical moments of local features. Also, we use a scalable learning and classification method which is substantially lighter than a SVM. Our method achieved performance comparable to state-of-the-art methods despite its remarkable simplicity.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hideki NAKAYAMA, Tatsuya HARADA, Yasuo KUNIYOSHI, "Dense Sampling Low-Level Statistics of Local Features" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 7, pp. 1727-1736, July 2010, doi: 10.1587/transinf.E93.D.1727.
Abstract: Generic image recognition techniques are widely studied for automatic image indexing. However, many of these methods are computationally too heavy for a practically large setup. Thus, for realizing scalability, it is important to properly balance the trade-off between performance and computational cost. In recent years, methods based on a bag-of-keypoints approach have been successful and widely used. However, the preprocessing cost for building visual words becomes immense in large-scale datasets. On the other hand, methods based on global image features have been used for a long time. Because global image features can be extracted rapidly, it is relatively easy to use them with large datasets. However, the performance of global feature methods is usually poor compared to the bag-of-keypoints methods. This paper proposes a simple but powerful scheme of boosting the performance of global image features by densely sampling low-level statistical moments of local features. Also, we use a scalable learning and classification method which is substantially lighter than a SVM. Our method achieved performance comparable to state-of-the-art methods despite its remarkable simplicity.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.1727/_p
Copy
@ARTICLE{e93-d_7_1727,
author={Hideki NAKAYAMA, Tatsuya HARADA, Yasuo KUNIYOSHI, },
journal={IEICE TRANSACTIONS on Information},
title={Dense Sampling Low-Level Statistics of Local Features},
year={2010},
volume={E93-D},
number={7},
pages={1727-1736},
abstract={Generic image recognition techniques are widely studied for automatic image indexing. However, many of these methods are computationally too heavy for a practically large setup. Thus, for realizing scalability, it is important to properly balance the trade-off between performance and computational cost. In recent years, methods based on a bag-of-keypoints approach have been successful and widely used. However, the preprocessing cost for building visual words becomes immense in large-scale datasets. On the other hand, methods based on global image features have been used for a long time. Because global image features can be extracted rapidly, it is relatively easy to use them with large datasets. However, the performance of global feature methods is usually poor compared to the bag-of-keypoints methods. This paper proposes a simple but powerful scheme of boosting the performance of global image features by densely sampling low-level statistical moments of local features. Also, we use a scalable learning and classification method which is substantially lighter than a SVM. Our method achieved performance comparable to state-of-the-art methods despite its remarkable simplicity.},
keywords={},
doi={10.1587/transinf.E93.D.1727},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Dense Sampling Low-Level Statistics of Local Features
T2 - IEICE TRANSACTIONS on Information
SP - 1727
EP - 1736
AU - Hideki NAKAYAMA
AU - Tatsuya HARADA
AU - Yasuo KUNIYOSHI
PY - 2010
DO - 10.1587/transinf.E93.D.1727
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2010
AB - Generic image recognition techniques are widely studied for automatic image indexing. However, many of these methods are computationally too heavy for a practically large setup. Thus, for realizing scalability, it is important to properly balance the trade-off between performance and computational cost. In recent years, methods based on a bag-of-keypoints approach have been successful and widely used. However, the preprocessing cost for building visual words becomes immense in large-scale datasets. On the other hand, methods based on global image features have been used for a long time. Because global image features can be extracted rapidly, it is relatively easy to use them with large datasets. However, the performance of global feature methods is usually poor compared to the bag-of-keypoints methods. This paper proposes a simple but powerful scheme of boosting the performance of global image features by densely sampling low-level statistical moments of local features. Also, we use a scalable learning and classification method which is substantially lighter than a SVM. Our method achieved performance comparable to state-of-the-art methods despite its remarkable simplicity.
ER -