Cartridge Case Image Mosaic Based on SIFT and Voting Mechanism

In the cartridge case marks detection, because of the limitations of microscope and the unsmoothed specimen surface, not all information can be obtained from just one image. This paper presents an efficient cartridge case mosaic approach to help experts´ analysis or computer recognition. Firstly, the initial matching is obtained by using scale invariant feature transform (SIFT). Secondly, the voting mechanism that combines adaptive K-means clustering angle and scale constraint algorithms is used to remove incorrect matches. Genetic Algorithm (GA) is applied to select the optimal combinations of parameters during the voting process. Finally, the fusion technology using histogram matching is adopted to smooth visible seams. The mosaic performance is evaluated through visual inspection and objective performance measurements, and results show the advantages of such approach compared to conventional approach.