Scene Categorization with Classified Codebook Model

Xu YANG; De XU; Songhe FENG; Yingjun TANG; Shuoyan LIU

doi:10.1587/transinf.E94.D.1349

Scene Categorization with Classified Codebook Model

Xu YANG, De XU, Songhe FENG, Yingjun TANG, Shuoyan LIU

Full Text Views

0

Share
Cite this

Summary :

This paper presents an efficient yet powerful codebook model, named classified codebook model, to categorize natural scene category. The current codebook model typically resorts to large codebook to obtain higher performance for scene categorization, which severely limits the practical applicability of the model. Our model formulates the codebook model with the theory of vector quantization, and thus uses the famous technique of classified vector quantization for scene-category modeling. The significant feature in our model is that it is beneficial for scene categorization, especially at small codebook size, while saving much computation complexity for quantization. We evaluate the proposed model on a well-known challenging scene dataset: 15 Natural Scenes. The experiments have demonstrated that our model can decrease the computation time for codebook generation. What is more, our model can get better performance for scene categorization, and the gain of performance becomes more pronounced at small codebook size.

Publication: IEICE TRANSACTIONS on Information Vol.E94-D No.6 pp.1349-1352

Publication Date: 2011/06/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E94.D.1349

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Cite this

Copy

Xu YANG, De XU, Songhe FENG, Yingjun TANG, Shuoyan LIU, "Scene Categorization with Classified Codebook Model" in IEICE TRANSACTIONS on Information, vol. E94-D, no. 6, pp. 1349-1352, June 2011, doi: 10.1587/transinf.E94.D.1349.
Abstract: This paper presents an efficient yet powerful codebook model, named classified codebook model, to categorize natural scene category. The current codebook model typically resorts to large codebook to obtain higher performance for scene categorization, which severely limits the practical applicability of the model. Our model formulates the codebook model with the theory of vector quantization, and thus uses the famous technique of classified vector quantization for scene-category modeling. The significant feature in our model is that it is beneficial for scene categorization, especially at small codebook size, while saving much computation complexity for quantization. We evaluate the proposed model on a well-known challenging scene dataset: 15 Natural Scenes. The experiments have demonstrated that our model can decrease the computation time for codebook generation. What is more, our model can get better performance for scene categorization, and the gain of performance becomes more pronounced at small codebook size.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1349/_p

Copy

@ARTICLE{e94-d_6_1349,
author={Xu YANG, De XU, Songhe FENG, Yingjun TANG, Shuoyan LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Scene Categorization with Classified Codebook Model},
year={2011},
volume={E94-D},
number={6},
pages={1349-1352},
abstract={This paper presents an efficient yet powerful codebook model, named classified codebook model, to categorize natural scene category. The current codebook model typically resorts to large codebook to obtain higher performance for scene categorization, which severely limits the practical applicability of the model. Our model formulates the codebook model with the theory of vector quantization, and thus uses the famous technique of classified vector quantization for scene-category modeling. The significant feature in our model is that it is beneficial for scene categorization, especially at small codebook size, while saving much computation complexity for quantization. We evaluate the proposed model on a well-known challenging scene dataset: 15 Natural Scenes. The experiments have demonstrated that our model can decrease the computation time for codebook generation. What is more, our model can get better performance for scene categorization, and the gain of performance becomes more pronounced at small codebook size.},
keywords={},
doi={10.1587/transinf.E94.D.1349},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Scene Categorization with Classified Codebook Model
T2 - IEICE TRANSACTIONS on Information
SP - 1349
EP - 1352
AU - Xu YANG
AU - De XU
AU - Songhe FENG
AU - Yingjun TANG
AU - Shuoyan LIU
PY - 2011
DO - 10.1587/transinf.E94.D.1349
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2011
AB - This paper presents an efficient yet powerful codebook model, named classified codebook model, to categorize natural scene category. The current codebook model typically resorts to large codebook to obtain higher performance for scene categorization, which severely limits the practical applicability of the model. Our model formulates the codebook model with the theory of vector quantization, and thus uses the famous technique of classified vector quantization for scene-category modeling. The significant feature in our model is that it is beneficial for scene categorization, especially at small codebook size, while saving much computation complexity for quantization. We evaluate the proposed model on a well-known challenging scene dataset: 15 Natural Scenes. The experiments have demonstrated that our model can decrease the computation time for codebook generation. What is more, our model can get better performance for scene categorization, and the gain of performance becomes more pronounced at small codebook size.
ER -