NTU: Solution for the object retrieval task of the ImageCLEF2007

• Main Author: HOI, Steven C. H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2007
• Subjects: Image Retrieval; Visual Word; Interest Point; Query Image; Image Patch; Computer Sciences; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/2409; https://ink.library.smu.edu.sg/context/sis_research/article/3409/viewcontent/NTU_Solution_ImageCLEF2007.pdf
• Institution: Singapore Management University

Object retrieval is an interdisciplinary research problem between object recognition and content-based image retrieval (CBIR). It is commonly expected that object retrieval can be solved more effectively with the joint maximization of CBIR and object recognition techniques. We study a typical CBIR solution with application to the object retrieval tasks [26,27]. We expect that the empirical study in this work will serve as a baseline for future research when using CBIR techniques for object recognition.