Limits...
A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval.

Zhang Y, Chen J, Huang X, Wang Y - PLoS ONE (2015)

Bottom Line: In this paper, we first analyze the effects of different sampling strategies for image retrieval, then we discuss feature pooling strategies on image retrieval performance with a probabilistic explanation in the context of sparse coding framework, and propose a modified sum pooling procedure which can improve the retrieval accuracy significantly.Further we apply sparse coding method to aggregate multiple types of features for large-scale image retrieval.Extensive experiments on commonly-used evaluation datasets demonstrate that our final compact image representation improves the retrieval accuracy significantly.

View Article: PubMed Central - PubMed

Affiliation: School of computer science & technology, Beijing Institute of Technology, Beijing, China.

ABSTRACT
Feature coding and pooling as a key component of image retrieval have been widely studied over the past several years. Recently sparse coding with max-pooling is regarded as the state-of-the-art for image classification. However there is no comprehensive study concerning the application of sparse coding for image retrieval. In this paper, we first analyze the effects of different sampling strategies for image retrieval, then we discuss feature pooling strategies on image retrieval performance with a probabilistic explanation in the context of sparse coding framework, and propose a modified sum pooling procedure which can improve the retrieval accuracy significantly. Further we apply sparse coding method to aggregate multiple types of features for large-scale image retrieval. Extensive experiments on commonly-used evaluation datasets demonstrate that our final compact image representation improves the retrieval accuracy significantly.

No MeSH data available.


Impact on retrieval accuracy with different combining parameters for SURF and color features.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4489107&req=5

pone.0131721.g007: Impact on retrieval accuracy with different combining parameters for SURF and color features.

Mentions: In this experiment we combine SURF feature with opponent color feature together under a sparse coding framework. We fix the color codebook size as 1K and change the SURF codebook size. Fig 7 described how the weight parameters (β1,β2) affect the retrieval accuracy in Zurich dataset with a 5K visual codebook. The parameters we used are approximate for UKB and Holidays datasets. Therefore in our experiments we choose β2 / β1 = 0.3 as an optimal weight ratio. Tables 6, 7 and 8 show image retrieval accuracy results with multiple features under a sparse coding framework on three datasets respectively.


A Probabilistic Analysis of Sparse Coded Feature Pooling and Its Application for Image Retrieval.

Zhang Y, Chen J, Huang X, Wang Y - PLoS ONE (2015)

Impact on retrieval accuracy with different combining parameters for SURF and color features.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4489107&req=5

pone.0131721.g007: Impact on retrieval accuracy with different combining parameters for SURF and color features.
Mentions: In this experiment we combine SURF feature with opponent color feature together under a sparse coding framework. We fix the color codebook size as 1K and change the SURF codebook size. Fig 7 described how the weight parameters (β1,β2) affect the retrieval accuracy in Zurich dataset with a 5K visual codebook. The parameters we used are approximate for UKB and Holidays datasets. Therefore in our experiments we choose β2 / β1 = 0.3 as an optimal weight ratio. Tables 6, 7 and 8 show image retrieval accuracy results with multiple features under a sparse coding framework on three datasets respectively.

Bottom Line: In this paper, we first analyze the effects of different sampling strategies for image retrieval, then we discuss feature pooling strategies on image retrieval performance with a probabilistic explanation in the context of sparse coding framework, and propose a modified sum pooling procedure which can improve the retrieval accuracy significantly.Further we apply sparse coding method to aggregate multiple types of features for large-scale image retrieval.Extensive experiments on commonly-used evaluation datasets demonstrate that our final compact image representation improves the retrieval accuracy significantly.

View Article: PubMed Central - PubMed

Affiliation: School of computer science & technology, Beijing Institute of Technology, Beijing, China.

ABSTRACT
Feature coding and pooling as a key component of image retrieval have been widely studied over the past several years. Recently sparse coding with max-pooling is regarded as the state-of-the-art for image classification. However there is no comprehensive study concerning the application of sparse coding for image retrieval. In this paper, we first analyze the effects of different sampling strategies for image retrieval, then we discuss feature pooling strategies on image retrieval performance with a probabilistic explanation in the context of sparse coding framework, and propose a modified sum pooling procedure which can improve the retrieval accuracy significantly. Further we apply sparse coding method to aggregate multiple types of features for large-scale image retrieval. Extensive experiments on commonly-used evaluation datasets demonstrate that our final compact image representation improves the retrieval accuracy significantly.

No MeSH data available.