On Vocabulary Size in Bag-of-Visual-Words Representation

被引：0

作者：

Hou, Jian ^{[1
]}

Kang, Jianxin ^{[1
]}

Qi, Naiming ^{[1
]}

机构：

[1] Harbin Inst Technol, Sch Astronaut, Harbin 150001, Peoples R China

来源：

ADVANCES IN MULTIMEDIA INFORMATION PROCESSING-PCM 2010, PT I | 2010年 / 6297卷

关键词：

Visual words; vocabulary size; straightforward matching; representative local descriptors;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Bag-of-visual-words is a popular image representation that produces high matching accuracy and efficiency. While vocabulary size impacts on matching accuracy, existing research usually selects the vocabulary size empirically. Research on representative local descriptors shows that with similarity based clustering, the intra-cluster similarity extent of descriptors plays the same role in straightforward matching as vocabulary size in visual words matching. Based on this observation, we propose to use similarity based clustering to determine the optimal vocabulary size for a given dataset in visual words matching. Preliminary experiments with three datasets produce encouraging results and demonstrate the potential of the proposed approach.

引用

页码：414 / 424

页数：11

共 50 条

[21] A Novel Bag-of-Visual-Words Approach for Geospatial Object Detection
Aytekin, Caglar
Alatan, A. Aydin
[J]. OPTICAL PATTERN RECOGNITION XXII, 2011, 8055
[22] Robust Acoustic Event Classification using Bag-of-Visual-Words
Mulimani, Manjunath
Koolagudi, Shashidhar G.
[J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3319 - 3322
[23] Pedestrian Detection Based on Bag-of-Visual-Words and SVM method
Li, Jun
Liao, Yuanjiang
Zhang, Hongmei
[J]. ADVANCES IN MECHATRONICS AND CONTROL ENGINEERING III, 2014, 678 : 189 - 192
[24] Bag-of-visual-words model for artificial pornographic images recognition
Fang-fang Li
Si-wei Luo
Xi-yao Liu
Bei-ji Zou
[J]. Journal of Central South University, 2016, 23 : 1383 - 1389
[25] Bag-of-Visual-Words Model for Classification of Interferometric SAR Images
Cagatay, Nazli Deniz
Datcu, Mihai
[J]. 11TH EUROPEAN CONFERENCE ON SYNTHETIC APERTURE RADAR (EUSAR 2016), 2016, : 243 - 246
[26] Evaluation of Random Forests on large-scale classification problems using a Bag-of-Visual-Words representation
Sole, Xavier
Ramisa, Arnau
Torras, Carme
[J]. ARTIFICIAL INTELLIGENCE RESEARCH AND DEVELOPMENT: RECENT ADVANCES AND APPLICATIONS, 2014, 269 : 273 - 276
[27] Spatial orientations of visual word pairs to improve Bag-of-Visual-Words model
Khan, Rahat
Barat, Cecile
Muselet, Damien
Ducottet, Christophe
[J]. PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2012, 2012,
[28] Extracting Emotions from Speech using a Bag-of-Visual-Words Approach
Spyrou, Evaggelos
Giannakopoulos, Theodoros
Sgouropoulos, Dimitrios
Papakostas, Michalis
[J]. 2017 12TH INTERNATIONAL WORKSHOP ON SEMANTIC AND SOCIAL MEDIA ADAPTATION AND PERSONALIZATION (SMAP 2017), 2017, : 80 - 83
[29] Stopwords Detection in Bag-of-Visual-Words: The Case of Retrieving Maya Hieroglyphs
Roman-Rangel, Edgar
Marchand-Maillet, Stephane
[J]. NEW TRENDS IN IMAGE ANALYSIS AND PROCESSING - ICIAP 2013, 2013, 8158 : 159 - 168
[30] Advancing Bag-of-Visual-Words Representations for Lesion Classification in Retinal Images
Pires, Ramon
Jelinek, Herbert F.
Wainer, Jacques
Valle, Eduardo
Rocha, Anderson
[J]. PLOS ONE, 2014, 9 (06):

← 1 2 3 4 5 →