Object recognition using bag of words with kernels for big data

Cheyu Wu; Ching-Te Chiu; Yar-Sun Hsu

doi:10.1109/ICCE-TW.2014.6904114

Back

Conference paper

Object recognition using bag of words with kernels for big data

Cheyu Wu, Ching-Te Chiu and Yar-Sun Hsu

Digest of Technical Papers - IEEE International Conference on Consumer Electronics, pp.89-90

18/09/2014

DOI: https://doi.org/10.1109/ICCE-TW.2014.6904114

Abstract

Scale Invariant Feature Transform (SIFT) descriptor can represent the object in detail, and is robust to variations due to image scaling and illumination changes. The challenge of using such descriptor to perform image retrieval in a large scale database is the high computational complexity. In this paper, we present the bag of words model combined with SIFT to reduce the computation cost. The average precision we get is about 30%. © 2014 IEEE.

Metrics

1 Record Views

Details

Title: Object recognition using bag of words with kernels for big data
Creators - without role: Cheyu Wu - National Tsing Hua University
Ching-Te Chiu - Department of Electrical Engineering, National Tsing Hua University
Yar-Sun Hsu - Department of Electrical Engineering, National Tsing Hua University
Publication Details: Digest of Technical Papers - IEEE International Conference on Consumer Electronics, pp.89-90
Grant note: Bureau of Foreign Trade;Department of Information
Identifiers: 9781479938308; 9957772105106774
Academic Unit: Institute of Information Systems and Applications, College of Electrical Engineering and Computer Science, National Tsing Hua University; National Tsing Hua University
Language: English
Resource Type: Conference paper

Object recognition using bag of words with kernels for big data

Abstract

Related links

Metrics

Details

National Tsing Hua University Social media