Analysis of curved line drawings using context and global information

We describe the analysis of visual scenes consisting of black on white drawings formed with curved lines, depicting familiar objects and forms: houses, trees, persons, and so on; for instance, drawings found in coloring books. The goal of such analysis is to recognize (by computer) such forms and shapes when present in the input scene; that is, to name (correctly) as many parts of the scene as possible: finger, hand, girl, dance, and so on. Complications occur because each input scene contains several such objects, partially occluding each other and in varying degrees of orientation, size, and so on. The analysis of these line drawings is an instance of'the context problem', which can be stated as'given that a set (a scene) is formed by components that locally (by their shape) are ambiguous, because each shape allows a component to have one of several possible values (a circle can be sun, ball, eye, hole) or meanings, can we make use of context information stated in the form of models, in order to single out for each component a value in such manner that the whole set (scene) is consistent or makes global sense?' Thus, shape drastically limits the values that a component could have, and further disambiguation is possible only by using global information (derived from several components and their interrelations or interconnections) under the assumption that the scene as a whole is meaningful. This paper proposes a way to solve'the context problem' in the paradigm of coloring book drawings. We have not implemented this approach; indeed, a purpose of this paper is to collect criticisms and suggestions.