Learning Shape Descriptions
نویسندگان
چکیده
We report on initial experiments with an implemented learning system whose inputs are images of two-dimensional shapes. The system first builds semantic network shape descriptions based on Brady's smoothed local symmetry representation. It learns shape models from them using a modified version of Winston's ANALOGY program. The learning program uses only positive examples, and is capable of learning disjunctive concepts. We discuss the lcarnability of shape descriptions.
منابع مشابه
Learning Symbolic Descriptions of 2d Shapes for Object Recognition in X-ray Images
This paper describes a method for learning shape descriptions of 2D objects in x-ray images. The descriptions are induced from shape examples using the AQ15c inductive learning system. The method has been experimentally compared to k-nearest neighbor, a statistical pattern recognition technique, and artificial neural networks. Experimental results demonstrate strong advantages of the AQ methodo...
متن کاملLearning Symbolic Descriptions of Shape for Object Recognition in X-ray Images
In this paper, we describe a method for learning shape descriptions of objects in x-ray images. The descriptions are induced from shape examples using the AQ15c inductive learning system. The method has been experimentally compared to k-nearest neighbor, a statistical pattern recognition technique, the C4.5 decision tree learning program, and a multilayer feed-forward neural network. Experiment...
متن کاملPerceptually Based Learning of Shape Descriptions
The Problem: In the past few years our group has developed sketching systems for several design domains, including mechanical engineering and software. Each new domain required writing new shape recognizers. We are currently developing a generic sketching system where a new domain can be added simply by providing textual descriptions of the domain symbols in a shape description language [1]. Ea...
متن کاملStyle Learning: Inductive Generalisation of Architectural Shape Patterns
Art historians and critics have defined the style as common features appeared in a class of objects. Abstract common features from a set of objects have been used as a bench mark for date and location of original works. Common features in shapes are identified by relationships as well as physical properties from shape descriptions. This paper will focus on how the computer recognises common sha...
متن کاملGeneric Shape Learning and Recognition1
We address the problem of generic shape recognition, in which exact models are not available. We propose an original approach, in which learning and recognition are intimately linked, as recognition is based on previous observation. The input to our system is in the form of segmented descriptions of objects in terms of parts. In 2-D, the shape is incrementally decomposed into parts suggested by...
متن کامل