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: 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.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.


Flowchart of our multiple feature sparse coding method.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0131721.g004: Flowchart of our multiple feature sparse coding method.

Mentions: After sparse coding and feature pooling, all sparse coded multiple feature vectors are concatenated into a single one with different weights, which is different from [14], the combination is represented as following:F=[β1Vsiftβ2Vcolor](14)The following Fig 4 illustrates the flowchart of our multiple feature sparse coding method. The final coding vector is then obtained by applying L2-normalization. PCA, LDA or product quantization [54] can further compress the aggregated image descriptor vector into a more compact one. The similarity measure between two images can be obtained by computing the cosine distances of image representation between the query image and train images.


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)

Flowchart of our multiple feature sparse coding method.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0131721.g004: Flowchart of our multiple feature sparse coding method.
Mentions: After sparse coding and feature pooling, all sparse coded multiple feature vectors are concatenated into a single one with different weights, which is different from [14], the combination is represented as following:F=[β1Vsiftβ2Vcolor](14)The following Fig 4 illustrates the flowchart of our multiple feature sparse coding method. The final coding vector is then obtained by applying L2-normalization. PCA, LDA or product quantization [54] can further compress the aggregated image descriptor vector into a more compact one. The similarity measure between two images can be obtained by computing the cosine distances of image representation between the query image and train images.

Bottom Line: 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.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.