Fusing multiple features and spatial information for image classification via codebook ensemble

被引：0

作者：

Luo H. ^{[1
]}

Wan C. ^{[1
]}

Guo M. ^{[1
]}

机构：

[1] School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou

来源：

International Journal of Embedded Systems | 2017年 / 9卷 / 03期

关键词：

Codebook ensemble; Feature fusion; Image classification;

D O I：

10.1504/IJES.2017.084691

中图分类号：

学科分类号：

摘要：

The construction of a codebook is an important step which is usually done by cluster analysis. However, clustering is a process that retains regions of high density in a distribution and it follows that the resulting codebook need not have discriminate properties. This paper presents a discriminative spatial codebook ensemble learning approach for image classification with three key innovations: 1) images are first divided into sub-regions according to a spatial pyramid, and then initial big member spatial codebooks are constructed by grouping features of sub-regions into a number of clusters, one member spatial codebook for one sub-region; 2) the discriminative member spatial codebook is formed by selecting the visual words with higher probability of occurring in the images. Then the features of each sub-region are coded by LLC based on its corresponding member codebook; 3) combining SIFT and KDES-G features to describe images is also proposed by generating a joint vector as a new feature vector. The experimental results on the Caltech101 and 15 scenes datasets have shown that the proposed method has better performance and robustness compared with some state-of-the-art works. Copyright © 2017 Inderscience Enterprises Ltd.

引用

页码：229 / 240

页数：11

共 28 条

[1]

Bo L., Ren X., Fox D., Kernel descriptors for visual recognition, Advances in Neural Information Processing Systems, 23, pp. 244-252, (2010)

[2]

Chang C.C., Lin C.J., LIBSVM: A library for support vector machines, ACM Transactions on Intelligent Systems and Technology (TIST), 2, 3, pp. 1-25, (2011)

[3]

Csurka G., Fan L., Willamowski J., Dance C.R., Bray C., Visual categorization with bags of keypoints, Workshop on Statistical Learning in Computer Vision Eccv., pp. 1-22, (2004)

[4]

Dalal N., Triggs B., Histograms of oriented gradients for human detection, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, pp. 886-893, (2005)

[5]

Gao C.X., Sang N., Unifying local features and filterbank features in the spatial pyramid matching model, Acta Electronica Sinica, 39, 9, pp. 2034-2038, (2011)

[6]

Gehler P., Nowozin S., On feature combination for multiclass object classification', Proceedings of the Twelfth, IEEE International Conference on Computer Vision, 30, 2, pp. 221-228, (2009)

[7]

Gemert J.C.V., Geusebroek J.M., Veenman C.J., Smeulders A.W.M., Kernel codebooks for scene categorization, ECCV, pp. 696-709, (2008)

[8]

Harzallah H., Jurie F., Schmid C., Combining efficient object localization and image classification, IEEE 12th International Conference on Computer Vision, pp. 237-244, (2009)

[9]

Koen V.D.S., Gevers T., Snoek C., Evaluating color descriptors for object and scene recognition, IEEE Transactions on Pattern Analysis & Machine Intelligence, 32, 9, pp. 1582-1596, (2010)

[10]

Lazebnik S., Schmid C., Ponce J., Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories, CVPR, pp. 2169-2178, (2006)

← 1 2 3 →