Dense Sampling Low-Level Statistics of Local Features
スポンサーリンク
概要
- 論文の詳細を見る
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.
- （社）電子情報通信学会の論文
- 2010-07-01
著者
-
Nakayama Hideki
Graduate School of Biological Sciences, Nara Institute of Science and Technology
-
Kuniyoshi Yasuo
Graduate School Of Information Science And Technology University Of Tokyo
-
Kuniyoshi Yasuo
Graduate School Of Information Science And Technology The University Of Tokyo
-
HARADA Tatsuya
Graduate School of Information Science and Technology, The University of Tokyo
-
Harada Tatsuya
Graduate School Of Information Science And Technology The University Of Tokyo
-
Nakayama Hideki
Graduate School Of Information Science And Technology The University Of Tokyo
-
Nakayama Hideki
Graduate School Of Biological Sciences Nara Institute Of Science And Technology (naist)
関連論文
- Floricultural Salvia plants have a high ability to eliminate bisphenol A(ENVIRONMENTAL BIOTECHNOLOGY)
- Improving salt tolerance in plant cells
- Floricultural Salvia plants have a high ability to eliminate bisphenol A
- Expression of OsHAK genes encoding potassium ion transporters in rice
- Functions of HKT transporters in sodium transport in roots and in protecting leaves from salinity stress
- High-Efficiency Secretory Production of Peroxidase Cla Using Vesicular Transport Engineering in Transgenic Tobacco(PLANT BIOTECHNOLOGY)
- Determination of the in vivo distribution of nuclear matrix attachment regions using a polymerase chain reaction-based assay in Arabidopsis thaliana(GENETICS, MOLECULAR BIOLOGY AND GENE ENGINEERING)
- Dense Sampling Low-Level Statistics of Local Features
- Academic Roadmap in Integrated Information Field
- Autonomous Adaptive Emergent Systems
- Molecular Cloning and Partial Characterization of a Peroxidase Gene Expressed in the Roots of Portulaca oleracea cv., One Potentially Useful in the Remediation of Phenolic Pollutants
- Molecular Cloning and Partial Characterization of a Peroxidase Gene Expressed in the Roots of Portulaca oleracea cv., One Potentially Useful in the Remediation of Phenolic Pollutants
- Improving salt tolerance in plant cells
- Activity of the C-terminal-Dependent Vacuolar Sorting Signal of Horseradish Peroxidase C1a is Enhanced by its Secondary Structure
- Isolation of polyphenol oxidase genes from Portulaca oleracea and evaluation of their ability to metabolize endocrine-disrupting chemicals
- Characterization of Bisphenol A Metabolites Produced by Portulaca oleracea cv. by Liquid Chromatography Coupled with Tandem Mass Spectrometry
- Isolation of polyphenol oxidase genes from Portulaca oleracea and evaluation of their ability to metabolize endocrine-disrupting chemicals
- Biomechanical Approach to Open-Loop Bipedal Running with a Musculoskeletal Athlete Robot