10 April 2018 Learning-to-rank approach to RGB-D visual search
Author Affiliations +
Both color and depth information may be deployed to seek by content through RGB-D imagery. Previous works dealing with global descriptors for RGB-D images advocate a decision level merger in which color and depth representations, independently computed, are juxtaposed to pursue a search for similarities. Differently, we propose a “learning-to-rank” paradigm aimed at weighting the two information channels according to the specific traits of the task and data at hand, thereby effortlessly addressing the potential diversity across applications. In particular, we propose a method, referred to as “kNN-rank,” which can learn the regularities among the outputs yielded by similarity-based queries. Another contribution concerns the “HyperRGBD” framework, a set of tools conceived to enable seamless aggregation of existing RGB-D datasets to obtain data featuring desired peculiarities and cardinality.
© 2018 SPIE and IS&T
Alioscia Petrelli, Alioscia Petrelli, Luigi Di Stefano, Luigi Di Stefano, "Learning-to-rank approach to RGB-D visual search," Journal of Electronic Imaging 27(5), 051212 (10 April 2018). https://doi.org/10.1117/1.JEI.27.5.051212 . Submission: Received: 13 January 2018; Accepted: 15 March 2018
Received: 13 January 2018; Accepted: 15 March 2018; Published: 10 April 2018


Color indexing with weak spatial constraints
Proceedings of SPIE (March 12 1996)
Multimedia database system with embedding MPEG-7 meta data
Proceedings of SPIE (December 26 2000)
Histogram as a measure of shape matching
Proceedings of SPIE (May 27 2004)
Image retrieval by using subpiece accumulative histogram
Proceedings of SPIE (September 25 2001)

Back to Top