Research on the Parameters of Feature Extraction and Matching Algorithms for Breech Face Comparisons

When a bullet is fired from a barrel, micro impression marks caused by the breech face on cartridge cases are one of the most critical factors in ballistic identification. This paper focuses on breech face impression images and introduces a scale invariant feature transform and progressive sample consensus integration algorithm to make an automated breech face comparison. scale invariant feature transform is used to extract invariant keypoints and build the feature descriptor for each keypoint. Progressive sample consensus, an improved algorithm based on the random sample consensus algorithm, is applied to eliminate error information and ensure a robust comparison result. Validation experiments were performed on an image set with a total of 40 breech face impression samples, giving 63 pairs of known matching and 717 pairs of known non-matching image comparisons. A variety of algorithms with different parameters were implemented to the image set to study how parameters affect the results. The results illustrate that the scale invariant feature transform and progressive sample consensus methods with the optimal parameters are highly precise and efficient for breech face impression comparisons.