Parks Connie L, Monson Keith L
Counterterrorism and Forensic Science Research Unit, Visiting Scientist Program, FBI Laboratory Division, 2501 Investigation Parkway, Quantico, VA 22135, United States.
Counterterrorism and Forensic Science Research Unit, FBI Laboratory Division, 2501 Investigation Parkway, Quantico, VA 22135, United States.
Forensic Sci Int. 2018 Jan;282:133-136. doi: 10.1016/j.forsciint.2017.11.013. Epub 2017 Nov 13.
This research examined how accurately 2D images (i.e., photographs) of 3D clay facial approximations were matched to corresponding photographs of the approximated individuals using an objective automated facial recognition system. Irrespective of search filter (i.e., blind, sex, or ancestry) or rank class (R, R, R, and R) employed, few operationally informative results were observed. In only a single instance of 48 potential match opportunities was a clay approximation matched to a corresponding life photograph within the top 50 images (R) of a candidate list, even with relatively small gallery sizes created from the application of search filters (e.g., sex or ancestry search restrictions). Increasing the candidate lists to include the top 100 images (R) resulted in only two additional instances of correct match. Although other untested variables (e.g., approximation method, 2D photographic process, and practitioner skill level) may have impacted the observed results, this study suggests that 2D images of manually generated clay approximations are not readily matched to life photos by automated facial recognition systems. Further investigation is necessary in order to identify the underlying cause(s), if any, of the poor recognition results observed in this study (e.g., potential inferior facial feature detection and extraction). Additional inquiry exploring prospective remedial measures (e.g., stronger feature differentiation) is also warranted, particularly given the prominent use of clay approximations in unidentified persons casework.
本研究使用客观的自动面部识别系统，检验了三维黏土面部模拟的二维图像（即照片）与被模拟个体的相应照片匹配的准确程度。无论采用何种搜索过滤器（即无筛选、按性别或按血统）或排名类别（R1、R2、R3和R4），均未观察到具有实际操作意义的结果。在48次潜在匹配机会中，只有一次黏土模拟与候选列表前50张图像（R1）中的相应生前照片匹配，即使在应用搜索过滤器（如性别或血统搜索限制）创建相对较小的图库时也是如此。将候选列表增加到包括前100张图像（R2），仅又产生了两例正确匹配的情况。尽管其他未测试的变量（如模拟方法、二维摄影过程和从业者技能水平）可能影响了观察结果，但本研究表明，自动面部识别系统不易将手动生成的黏土模拟的二维图像与生前照片进行匹配。有必要进行进一步调查，以确定本研究中观察到的识别结果不佳的潜在原因（如有）（例如面部特征检测和提取可能较差）。鉴于黏土模拟在身份不明人员案件工作中的广泛应用，对探索前瞻性补救措施（如更强的特征区分）的额外调查也很有必要。
