scispace - formally typeset
Search or ask a question

Showing papers on "Sketch recognition published in 1990"


Proceedings ArticleDOI
04 Dec 1990
TL;DR: BONSAI identifies and localizes 3-D objects in range images of one or more parts which have been designed on a CAD system via constrained search of the interpretation tree, using unary and binary constraints to prune the search space.
Abstract: A description is presented of BONSAI, a model-based 3-D object recognition system, which identifies and localizes 3-D objects in range images of one or more parts which have been designed on a CAD system. Recognition is performed via constrained search of the interpretation tree, using unary and binary constraints (derived automatically from the CAD models) to prune the search space. Experiments with over 200 images of 20 different parts demonstrate that the constrained search approach to 3-D object recognition has comparable accuracy to other existing systems. >

28 citations


Journal ArticleDOI
TL;DR: Sketch recognition is applied to freehand architectural drawings to recognize the architect's intentions from a quick sketch and generate a detailed drawing.
Abstract: Sketch recognition is applied to freehand architectural drawings. The purpose is to recognize the architect's intentions from a quick sketch and generate a detailed drawing. The system can also calibrate itself to interpret the peculiar styles of each individual architect using it.

12 citations




01 Jan 1990
TL;DR: In this paper, a new computer model for automatic sketch interpretation is proposed, based on existing works on cognitive models of the human visual system, which can be used for sketch interpretation.
Abstract: Despite the large availability of powerful and innovative computer tools, freehand sketch remains used by most designers to support their creative work. Consequently, automatic sketch interpretation offers many opportunities for the exploitation of CAD tools and evaluation algorithms from the early stages of a design project. A sketch contains by nature many ambiguities that arise mostly from the inaccuracy of freehand drawing and from the omnipresence of implicit meanings. Therefore, the interpretation space (the set of possible interpretations) may quickly become very large, making any exhaustive exploration impossible. Starting from existing works on cognitive models of the human visual system, we propose a new computer model for automatic sketch interpretation.