In this paper, we propose a framework for engineering drawings recognition using a case-based approach. The key idea of our scheme is that, interactively, the user provides an example of one type of graphic object in an engineering drawing, then the system learns the graphical knowledge of this type of graphic object from the example and uses this learned knowledge to recognize or search for similar graphic objects in engineering drawings. The scheme emphasizes the following three distinct characteristics: automatism, run-time-ness, and robustness. We summarized five types of geometric constraints to represent the generic graphical knowledge. We also developed two algorithms for case-based graphical knowledge acquisition and knowledge-based graphics recognition, respectively. Experiments have shown that our proposed framework is both efficient and effective for recognizing various types of graphic objects in engineering drawings.