The image retrieval paradigm has evolved from low-level image representations to semantic concept models to higher-level semantic inferences. UCSD's Statistical Visual Computing Laboratory has developed effective techniques for each paradigm that equate retrieval with classification and strive for minimum-probability-of-error optimality.
Index Terms:
image retrieval systems
Citation:
Nuno Vasconcelos, "From Pixels to Semantic Spaces: Advances in Content-Based Image Retrieval," Computer, vol. 40, no. 7, pp. 20-26, July 2007, doi:10.1109/MC.2007.239