Relevance feedback and latent semantic index based cultural relic image retrieval
Edutainment'07 Proceedings of the 2nd international conference on Technologies for e-learning and digital entertainment
A relevance feedback-based learner for image retrieval using SIFT descriptors
International Journal of Computational Vision and Robotics
Multimodal retrieval with relevance feedback based on genetic programming
Multimedia Tools and Applications
| Hi-index | 0.00 |
Relevance Feedback (RF) is a powerful technique inContent-Based Image Retrieval (CBIR) system and hasbecome a very active research topic in the past few years.At the early stage of CBIR, research primarily focused onexploring various feature representation and ignored thesubjectivity of human perception. There exists a gapbetween high-level concepts and low-level features. As aneffective solution, the RF technique has been used on manyCBIR systems to improve the retrieval precision. In thispaper, a novel relevance feedback method is proposed toimprove the retrieval performance of CBIR. By moving thequery vector and updating the weighting factorssimultaneously, the convergence speed of the relevancefeedback retrieval is accelerated. Experimental resultsshow that this method achieves high accuracy andeffectiveness in CBIR.