The invention discloses a composite
grinding machining feature automatic identification method based on a part
engineering image. The method comprises two main body steps of geometric contour extraction and process
feature matching. The external features and the internal features are respectively represented by a
solid line frame and a dotted line frame, and the geometric contour extraction is divided into two stages, so that the problem of automatic identification of intersection features generally existing in an automatic feature
identification technology is solved. The feature geometric contour extraction is based on a boundary tracking
algorithm, an effective contour of each feature represented by four
angular point pixels is obtained, a CNN classifier is utilized to classify whether internal features exist in a part or not, and finally effective automatic recognition of multiple manufacturing features is sequentially carried out according to geometric information. The method doesnot depend on any CAD tool or
data exchange standard, various typical composite
grinding machining features can be automatically extracted, high pixel-level precision is guaranteed, and development and application based on the method are lighter and convenient to transplant.