Research into techniques for the retrieval of images by semantic content is
still in its infancy. This paper reviews recent trends in the field, disti
nguishing four separate lines of activity: automatic scene analysis, model-
based and statistical approaches to object classification, and adaptive lea
rning from user feedback. It compares the strengths and weaknesses of model
-based and adaptive techniques, and argues that further advances in the fie
ld are likely to involve the increasing use of techniques from the field of
artificial intelligence. (C) 2001 Pattern Recognition Society. Published b
y Elsevier Science Ltd. All rights reserved.