VisualSEEk: a fully automated content-based image query system
MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
Visual Image Retrieval by Elastic Matching of User Sketches
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learnable visual keywords for image classification
Proceedings of the fourth ACM conference on Digital libraries
A unified framework for semantics and feature based relevance feedback in image retrieval systems
MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Blobworld: A System for Region-Based Image Indexing and Retrieval
VISUAL '99 Proceedings of the Third International Conference on Visual Information and Information Systems
Dominant Color Region Based Indexing for CBIR
ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
Automatic image annotation and retrieval using cross-media relevance models
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Hi-index | 0.00 |
In this paper, we proposed an auto annotation image retrieval system. In our system, an image was segmented into regions, each of which corresponds to an object. The regions identified by region-based segmentation are more consistent with human cognition than those identified by block-based segmentation. According to the object's visual features (color and shape), new objects will be map to the similar clusters to obtain its associated semantic concept. The semantic concepts derived by the training images may not be the same as the real semantic concepts of the underlying images, because the former concepts depend on the low-level visual features. To ameliorate this problem, we propose a relevance-feedback model to learn the long-term and short-term interests of users. The experiments show that the proposed algorithm outperforms the traditional co-occurrence model about 19.5%; furthermore, after five times of relevance feedback, the mean average precision improves from 46% to 62.7%.