Object recognition based on the region of interest and optical bag of words model

Authors:
Weisheng Li;Peng Dong
Affiliations:
Chongqing University of Posts and Telecommunications, Chongqing, China;Chongqing University of Posts and Telecommunications, Chongqing, China
Venue:
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Year:
2013

Citing 12
Cited 0

Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
A Bayesian Hierarchical Model for Learning Natural Scene Categories

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Object Recognition with Features Inspired by Visual Cortex

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
k-means++: the advantages of careful seeding

SODA '07 Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context

International Journal of Computer Vision
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Visual object recognition using DAISY descriptor

ICME '11 Proceedings of the 2011 IEEE International Conference on Multimedia and Expo
Contextual Object Localization With Multiple Kernel Nearest Neighbor

IEEE Transactions on Image Processing
Exploiting local and global patch rarities for saliency detection

CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Object-Centric spatial pooling for image classification

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

To overcome the disadvantages of general object recognition methods based on traditional Bag of Words, this paper proposed a method for object recognition based on Region of Interest (ROI) and optimal Bag of Words model (BOW). Firstly, extracting the ROI, the interest image, whose features are detected and described using the Scale Invariant Feature Transform (SIFT). Secondly, constructing a visual codebook by clustering the feature vectors using K-means++ cluster algorithm. Thirdly, the mapping relationships between the vectors and visual codebook are computed to construct a visual word histogram that represents the image. Finally, The Support Vector Machine (SVM) is utilized to perform image classification and recognition. The experiments are performed on the MSRC 21-class database. The results show that the recognition accuracy of the proposed method is better than the traditional object recognition methods.