Your SlideShare is downloading. ×
Wiamis2010 Pres
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×

Introducing the official SlideShare app

Stunning, full-screen experience for iPhone and Android

Text the download link to your phone

Standard text messaging rates apply

Wiamis2010 Pres

229
views

Published on

It is widely acknowledged that good performances of content-based image retrieval systems can be attained by adopting relevance feedback mechanisms. One of the main difficulties in exploiting relevance …

It is widely acknowledged that good performances of content-based image retrieval systems can be attained by adopting relevance feedback mechanisms. One of the main difficulties in exploiting relevance information is the availability of few relevant images, as users typically label a few dozen of images, the majority of them often being non-relevant to user’s needs. In order to boost the learning capabilities of relevance feedback techniques, this paper proposes the creation of points in the feature space which can be considered as representation of relevant images. The new points are generated taking into account not only the available relevant points in the feature space, but also the relative positions of non-relevant ones. This approach has been tested on a relevance feedback technique, based on the Nearest-Neighbor classification paradigm. Reported experiments show the effectiveness of the proposed technique relatively to precision and recall.


0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
229
On Slideshare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
3
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. PhD Program in Electronic and Computer Engineering PhD School in Information Engineering K-Nearest Neighbors Directed Synthetic Images Injection Luca Piras [email_address] Giorgio Giacinto [email_address] Group R A P Pattern Recognition and Applications Group http://prag.diee.unica.it/pra/eng/home WIAMIS 2010
  • 2.
    • Relevance feedback
    • Relevance feedback techniques are employed to capture the subjectivity of retrieval results and to refine the search:
    • The user is asked to label the images as being relevant or not
    • The similarity measure is modified accordingly
    • Lack of relevant images
    • Even in the case of very “cooperative” users, it is not feasible to display more than a few dozens of images to label.
    • If the database at hand is very large, then the number of images that are relevant to the query can easily be very small compared to the size of the database.
    • In a high dimensional feature space images with different semantic content can lie near each other.
    Group R A P Pattern Recognition and Applications Group http://prag.diee.unica.it/pra/eng/home WIAMIS 2010 K-NEAREST NEIGHBORS DIRECTED SYNTHETIC IMAGES INJECTION Luca Piras , Giorgio Giacinto Dept. of Electrical and Electronic Engineering - University of Cagliari, Italy luca.piras@diee.unica.it - giacinto@diee.unica.it
  • 3.
    • Our proposal
    • Increasing the number of “relevant” patterns used to train the system:
    • Creating new random artificial patterns by exploiting nearest neighbor information.
    • Constraining these patterns in a region of the feature space containing relevant images.
    • Constraints
    • Choice of the images from which creating new patterns
    • Number of new patterns
    • Boundary of the permitted generating area
    Conclusion The experiments show the proposed technique allows improving the performances of a relevance feedback mechanism based on Nearest-Neighbors. Group R A P Pattern Recognition and Applications Group http://prag.diee.unica.it/pra/eng/home WIAMIS 2010 K-NEAREST NEIGHBORS DIRECTED SYNTHETIC IMAGES INJECTION Luca Piras , Giorgio Giacinto Dept. of Electrical and Electronic Engineering - University of Cagliari, Italy luca.piras@diee.unica.it - giacinto@diee.unica.it