A novel optimization-based approach for content-based image retrieval

Content-based image retrieval is nowadays one of the possible and promising solutions to manage image databases effectively. However, with the large number of images, there still exists a great discrepancy between the users' expectations (accuracy and efficiency) and the real performance in image retrieval. In this work, new optimization strategies are proposed on vocabulary tree building, retrieval, and matching methods. More precisely, a new clustering strategy combining classification and conventional K -Means method is firstly redefined. Then a new matching technique is built to eliminate the error caused by large-scaled scale-invariant feature transform (SIFT). Additionally, a new unit mechanism is proposed to reduce the cost of indexing time. Finally, the numerical results show that excellent performances are obtained in both accuracy and efficiency based on the proposed improvements for image retrieval.