Loading...

Design a Content-Based Color Image Retrieval Using Attention Driven Saliency Map

Ebrahimi, Davood | 2012

715 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 43253 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Fatemizadeh, Emadeddin
  7. Abstract:
  8. Content Based Image Retrieval (CBIR) is in fact an image search engine which Operates on image Context . in this thesis (project) the aim was to use the Visual attention of humans in detecting the objects in image. in this ability first a salient image of the most important things in the image would be created And after an initial separation , for the final recognition the other features (details) in the image will be used It’s a while that the use of Visual attention models and saliency maps in designing the interfaces between humans and machines has been considered widely. This fact in the design of CBIR systems has not a good background (satisfying history). In this thesis I have introduced some methods for image retrieval based on Visual attention. To achieve this goal I used saliency map . the results show that the usage of saliency map for retrieving , has enhanced the accuracy of retrieval and would let the system to choose the desired domains in the image for defining features. The image data base for this project were a set of 10000 images selected from Corel Data base. in the survey done , for 8 classes out of ten , the usage of saliency map has enhaced the accuracy and for two classes the results were not satisfying. Saliency map in the horse class has enhanced the accuracy to 29% and in the dinosaur class the reduction was 47% in respect to earlier results. In the comparison done with simplicity system which is a well know retrieval system , the proposed method in 8 classes had better results , in one class the results were the same And in one class the results were awful
  9. Keywords:
  10. Image Retrieval ; Interest Region ; Visual Attention ; Saliency Map

 Digital Object List

  • محتواي پايان نامه
  •   view

 Bookmark

...see more