In order to solve the problem of lack of feature extraction dimension for typical defects in X-ray images of aluminum alloy die castings

and a large number of manual interventions affecting the accuracy of feature extraction

a typical defect feature extraction algorithm for X-ray imaging of aluminum alloy die castings was put forward. Multiple analysis dimensions for typical defects such as pore

misrun and deformation in aluminum alloy die castings was carried out. Filtering denoising

threshold segmentation and other methods were applied to preprocess the die casting image

and multi-dimensional features such as perimeter and area were extracted to realize automatic feature extraction of pores and slag inclusion defects. The experimental results on aluminum alloy die castings actually produced by some enterprises show that this method can effectively extract the typical defect features of aluminum alloy die castings

providing reference for subsequent defect detection and identification.