Keypoint selection for efficient bag-of-words feature generation and effective image classification

NCU Institutional Repository > 管理學院 > 資訊管理學系 > 期刊論文 > Item 987654321/106806

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/106806

题名:	Keypoint selection for efficient bag-of-words feature generation and effective image classification
作者:	蔡志豐;Lin, Wei-Chao;Tsai, Chih-Fong;Chen, Zong-Yao;Ke, Shih-Wen
贡献者:	管理學院資訊管理學系
关键词:	Bag-of-words;Classification;Computational efficiency;Image classification;Iterative methods;Keypoint selection;Object categorization;Pascal (programming language);Representations;Support vector machines;Vector quantization
日期:	2016-02-01
上传时间:	2026-04-23 13:43:49 (UTC+8)
出版者:	Elsevier Inc.;Elsevier Inc
摘要:	摘要： One of the most popular image representations for image classification is based on the bag-of-words (BoW) features. However, the number of keypoints that need to be detected from images to generate the BoW features is usually very large, which causes two problems. First, the computational cost during the vector quantization step is high. Second, some of the detected keypoints are not helpful for recognition. To resolve these limitations, we introduce a framework, called iterative keypoint selection (IKS), with which to select representative keypoints for accelerating the computational time to generate the BoW features, leading to more discriminative feature representation. Each iteration in IKS is comprised of two steps. In the first step some representative keypoint(s) are identified from each image. Then, the keypoints are filtered out if the distances between them and the identified representative keypoint(s) are less than a pre-defined distance. The iteration process continues until no unrepresentative keypoints can be found. Two specific approaches are proposed to perform the first step of IKS. IKS1 focuses on randomly selecting one representative keypoint and IKS2 is based on a clustering algorithm in which the representative keypoints are the closest points to their cluster centers. Experiments carried out based on the Caltech 101, Caltech 256, and PASCAL 2007 datasets demonstrate that performing keypoint selection using IKS1 and IKS2 to generate both the BoW and spatial-based BoW features allows the support vector machine (SVM) classifier to provide better classification accuracy than with the baseline features without keypoint selection. However, it is found that the computational cost of IKS1 is larger than the baseline methods. On the other hand, IKS2 is able to not only efficiently generate the BoW and spatial-based features that reduce the computational time for vector quantization over these datasets, but also provides better classification results than IKS1 over the PASCAL 2007 and Caltech 256 datasets. 出版者： Elsevier Inc 出版日期： 2016-02-01 出處： Information sciences, 2016-02, Vol.329, p.33-51 資源來源： ScienceDirect (Elsevier) Journals 版權： 2015 Elsevier Inc. 識別號： ISSN: 0020-0255 識別號： EISSN: 1872-6291 識別號： DOI: 10.1016/j.ins.2015.08.021
显示于类别:	[資訊管理學系] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	27	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....