摘要：To make a bridge between engineering information and the geometry of product model, it is crucial to manipulate product model with form features containing high-level engineering information. In recent years much research has been undergone in the area of form feature recognition. In many previous works form feature recognition usually starts with a finished CAD model. The shape of a finished model consisted of a number of features is much more complex than that of a single feature. This problem was ignored by many previous works. In this paper a completely context-independed method is provided. In designing the part,. the feature-based model is decomposed into a quasi-feature-based one that can be converted into various context-oriented feature models required by specific context-oriented applications. In order to decompose features into quasi-features which have convex volumes, this paper proposes a method which integrates modelling with decomposition.