Abstract:Aircraft sheet metal parts need to be painted after forming. The classification and recognition of a large number of different kinds of sheet metal parts after batch painting has been performed manually, which is a tedious and difficult work. An imagebased crossgrained recognition method for aircraft sheet metal parts is proposed to deal with this tough problem. A specific image collection platform is designed and constructed to take the images of the sheet metal parts in both top and side angles. The images of the sample parts, together with the extracted tendimensional (10D) feature vectors composed of shape factors and invariant moments, are stored in a database for the later use of recognition. According to the features of numerous kinds of sheet metal parts and the existence of groups of sheet metal parts with high similarity, the coarsegrained recognition method is designed. Through traversing and comparing the 10D feature vectors, the 2 candidate targets of the given sheet metal part to be recognized with top similarity are found from the database. Then, the finegrained recognition method, which is a manmachine cooperation process, is used to achieve the finally recognition of the expected sheet metal part. In the experiments on 20 different kinds of aircraft sheet metal parts, the proposed method achieves a recognition accuracy of 960%, and the whole recognition procedure is simple, convenient and efficient.