Abstract. Visual dictionary learning and base (binary) classifier training are two basic problems for the recently most popular image categorization framework, which is based on t...
We use relaxation to produce painted imagery from images and video. An energy function is first specified; we then search for a painting with minimal energy. The appeal of this st...
Rule extraction is a technique aimed at transforming highly accurate opaque models like neural networks into comprehensible models without losing accuracy. G-REX is a rule extract...
This paper presents a formal framework for designing search algorithms which can identify target images by the spatial distribution of color, edge and texture attributes. The fram...
We prove that the concept class of disjunctions cannot be pointwise approximated by linear combinations of any small set of arbitrary real-valued functions. That is, suppose that t...