Hierarchical BoW with segmental sparse coding for large scale image classification and retrieval

doi:10.1007/s11042-018-5955-z

	Hierarchical BoW with segmental sparse coding for large scale image classification and retrieval
	Zhou, Jianshe 1; Narentuya 1; Tang, Sheng 2; Liu, Jie 3
	2018-09-01
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
ISSN	1380-7501
卷号	77 期号:17 页码:22319-22338
摘要	The bag-of-words (BoW) has been widely regarded as the most successful algorithms for content-based image related tasks, such as large scale image retrieval, classification, and object categorization. Large visual words acquired by BoW quantization through large vocabulary or codebooks have been receiving much attention in the past years. However, not only construction of large vocabulary but also the quantization process impose a heavy burden in terms of time and memory complexities. In order to tackle this issue, we propose an efficient hierarchical BoW (HBoW) to achieve large visual words through quantization by a compact vocabulary instead of large vocabulary. Our vocabulary is very compact since it is only composed of two small dictionaries which is learned through segmental sparse decomposition of local features. To generate the BoW with large size, we first divide the local features into two half parts, and use the two small dictionaries to compute their sparse codes. Then, we map the two indices of the maximum elements of the two sparse codes to a large set of visual words based upon the fact that data with similar properties will share the same base weighted with the largest sparse coefficient. To further make similar patches have higher probability of select the same dictionary base to get similar BoW vectors, we propose a novel collaborative dictionary learning method by imposing the similarity regularization factor together with the row sparsity regularization across data instances during group sparse coding. Additionally, based on index combination of top-2 large sparse codes of local descriptors, we propose a soft BoW assignment method so that our proposed HBoW can tolerate different word selection for similar patches. By employing the inverted file structure built through our HBoW, K-nearest neighbors (KNN) can be efficiently retrieved. After incorporation of our fast KNN search into the SVM-KNN classification method, our HBoW can be used for efficient image classification and logo recognition. Experiments on serval well-known datasets show that our approach is effective for large scale image classification and retrieval.
关键词	Bag of words Dictionary learning Sparse coding Image retrieval Image classification
DOI	10.1007/s11042-018-5955-z
收录类别	SCI
语种	英语
资助项目	National Nature Science Foundation of China[61371194] ; National Nature Science Foundation of China[61672361] ; Beijing Natural Science Foundation[4152012] ; Beijing Advanced Innovation Center for Imaging Technology[BAICIT-2016009]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000441364500032
出版者	SPRINGER
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/5090
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Jie
作者单位	1.Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Technol, Beijing 100048, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Capital Normal Univ, Coll Informat & Engn, Beijing 100048, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Jianshe,Narentuya,Tang, Sheng,et al. Hierarchical BoW with segmental sparse coding for large scale image classification and retrieval[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2018,77(17):22319-22338.
APA	Zhou, Jianshe,Narentuya,Tang, Sheng,&Liu, Jie.(2018).Hierarchical BoW with segmental sparse coding for large scale image classification and retrieval.MULTIMEDIA TOOLS AND APPLICATIONS,77(17),22319-22338.
MLA	Zhou, Jianshe,et al."Hierarchical BoW with segmental sparse coding for large scale image classification and retrieval".MULTIMEDIA TOOLS AND APPLICATIONS 77.17(2018):22319-22338.