Quantitative Statistics and Identification of Tool‐Marks

• Yang, Min ^[2] ; Mou, Li ^[3] ; Fu, Yi‐Ming ^[2] ; Wang, Yu ; Wang, Jiang‐feng ^[1]
  1. [1] Soochow University

     Soochow University

     China

     
  2. [2] Department of Forensic Science, Guangdong Police College.China
  3. [3] Department of Computer Science and Technology, Guangdong Police Colleg.China

  Mostrar afiliaciones +
• Localización: Journal of forensic sciences, ISSN-e 1556-4029, ISSN 0022-1198, Vol. 64, Nº. 5, 2019, págs. 1324-1334
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • This study was designed to establish a feature identification method of tool-mark 2D data. A uniform local binary pattern his-togram operator was developed to extract the tool-mark features, and the random forest algorithm was adopted to identify these. The presentedmethod was used to conduct five groups of experiments with a 2D dataset of known matched and nonmatched tool-marks made by bolt clip-pers, cutting pliers, and screwdrivers. The experimental results show that the proposed method achieved a high rate of identification of thetool-mark samples generated under identical conditions. The proposed method effectively overcomes the disadvantage of unstable illuminationof 2D tool-mark image data and avoids the difficulty in mark inspection caused by manually preset parameters in the existing methods, thusreducing the uncertainty of inspected results.