Supervised Feature Quantization with Entropy Optimization
Författare
Summary, in English
Feature quantization is a crucial component for efficient large scale image retrieval and object recognition. By quantizing local features into visual words, one hopes that features that match each other obtain the same word ID. Then, similarities between images can be measured with respect to the corresponding histograms of visual words. Given the appearance variations of local features, traditional quantization methods do not take into account the distribution of matched features. In this paper, we investigate how to encode additional prior information on the feature distribution via entropy optimization by leveraging ground truth correspondence data. We propose a computationally efficient optimization scheme for large scale vocabulary training. The results from our experiments suggest that entropy-optimized vocabulary performs better than unsupervised quantization methods in terms of recall and precision for feature matching. We also demonstrate the advantage of the optimized vocabulary for image retrieval.
Avdelning/ar
- Matematik LTH
- Mathematical Imaging Group
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
Publiceringsår
2011
Språk
Engelska
Sidor
1386-1393
Publikation/Tidskrift/Serie
Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on
Dokumenttyp
Konferensbidrag
Förlag
IEEE - Institute of Electrical and Electronics Engineers Inc.
Ämne
- Computer Vision and Robotics (Autonomous Systems)
- Mathematics
Nyckelord
- visual vocabulary
- entropy optimization
Conference name
1st IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition (ICCV 2011), 2011
Conference date
2011-11-06 - 2011-11-13
Conference place
Barcelona, Spain
Status
Published
Forskningsgrupp
- Mathematical Imaging Group
ISBN/ISSN/Övrigt
- ISBN: 978-1-4673-0062-9 (print)