Cao Kai, Jain Anil K
IEEE Trans Pattern Anal Mach Intell. 2019 Apr;41(4):788-800. doi: 10.1109/TPAMI.2018.2818162. Epub 2018 Mar 22.
Latent fingerprints are one of the most important and widely used evidence in law enforcement and forensic agencies worldwide. Yet, NIST evaluations show that the performance of state-of-the-art latent recognition systems is far from satisfactory. An automated latent fingerprint recognition system with high accuracy is essential to compare latents found at crime scenes to a large collection of reference prints to generate a candidate list of possible mates. In this paper, we propose an automated latent fingerprint recognition algorithm that utilizes Convolutional Neural Networks (ConvNets) for ridge flow estimation and minutiae descriptor extraction, and extract complementary templates (two minutiae templates and one texture template) to represent the latent. The comparison scores between the latent and a reference print based on the three templates are fused to retrieve a short candidate list from the reference database. Experimental results show that the rank-1 identification accuracies (query latent is matched with its true mate in the reference database) are 64.7 percent for the NIST SD27 and 75.3 percent for the WVU latent databases, against a reference database of 100K rolled prints. These results are the best among published papers on latent recognition and competitive with the performance (66.7 and 70.8 percent rank-1 accuracies on NIST SD27 and WVU DB, respectively) of a leading COTS latent Automated Fingerprint Identification System (AFIS). By score-level (rank-level) fusion of our system with the commercial off-the-shelf (COTS) latent AFIS, the overall rank-1 identification performance can be improved from 64.7 and 75.3 to 73.3 percent (74.4 percent) and 76.6 percent (78.4 percent) on NIST SD27 and WVU latent databases, respectively.
潜在指纹是全球执法和法医机构中最重要且使用最广泛的证据之一。然而，美国国家标准与技术研究院（NIST）的评估表明，最先进的潜在指纹识别系统的性能远不能令人满意。一个高精度的自动潜在指纹识别系统对于将犯罪现场发现的潜在指纹与大量参考指纹进行比对以生成可能匹配对象的候选列表至关重要。在本文中，我们提出了一种自动潜在指纹识别算法，该算法利用卷积神经网络（ConvNets）进行纹线流估计和细节特征描述符提取，并提取互补模板（两个细节特征模板和一个纹理模板）来表示潜在指纹。基于这三个模板的潜在指纹与参考指纹之间的比对分数被融合，以从参考数据库中检索出一个短候选列表。实验结果表明，对于NIST SD27数据库，在面对包含10万个捺印指纹的参考数据库时，排名第一的识别准确率（查询的潜在指纹与参考数据库中其真实匹配对象匹配）为64.7%；对于西弗吉尼亚大学（WVU）潜在指纹数据库，该准确率为75.3%。这些结果在已发表的关于潜在指纹识别的论文中是最好的，并且与领先的商用现货（COTS）潜在自动指纹识别系统（AFIS）的性能（在NIST SD27和WVU数据库上的排名第一准确率分别为66.7%和70.8%）具有竞争力。通过将我们的系统与商用现货（COTS）潜在AFIS进行分数级（排名级）融合，在NIST SD27和WVU潜在指纹数据库上，整体排名第一的识别性能分别可以从64.7%和75.3%提高到73.3%（74.4%）和76.6%（78.4%）。
