Diverse types of expertise in facial recognition.

Facial recognition errors can jeopardize national security, criminal justice, public safety and civil rights. Here, we compare the most accurate humans and facial recognition technology in a detailed lab-based evaluation and international proficiency test for forensic scientists involving 27 forensic departments from 14 countries. We find striking cognitive and perceptual diversity between naturally skilled super-recognizers, trained forensic examiners and deep neural networks, despite them achieving equivalent accuracy. Clear differences emerged in super-recognizers' and forensic examiners' perceptual processing, errors, and response patterns: super-recognizers were fast, biased to respond 'same person' and misidentified people with extreme confidence, whereas forensic examiners were slow, unbiased and strategically avoided misidentification errors. Further, these human experts and deep neural networks disagreed on the similarity of faces, pointing to differences in their representations of faces. Our findings therefore reveal multiple types of facial recognition expertise, with each type lending itself to particular facial recognition roles in operational settings. Finally, we show that harnessing the diversity between individual experts provides a robust method of maximizing facial recognition accuracy. This can be achieved either via collaboration between experts in forensic laboratories, or most promisingly, by statistical fusion of match scores provided by different types of expert.

Interpol review of imaging and video 2016-2019.

This review paper covers the forensic-relevant literature in imaging and video analysis from 2016 to 2019 as a part of the 19th Interpol International Forensic Science Managers Symposium. The review papers are also available at the Interpol website at: https://www.interpol.int/content/download/14458/file/Interpol%20Review%20Papers%202019.pdf.

Critical review of the use and scientific basis of forensic gait analysis.

This review summarizes the scientific basis of forensic gait analysis and evaluates its use in the Netherlands, United Kingdom and Denmark, following recent critique on the admission of gait evidence in Canada. A useful forensic feature is (1) measurable, (2) consistent within and (3) different between individuals. Reviewing the academic literature, this article found that (1) forensic gait features can be quantified or observed from surveillance video, but research into accuracy, validity and reliability of these methods is needed; (2) gait is variable within individuals under differing and constant circumstances, with speed having major influence; (3) the discriminative strength of gait features needs more research, although clearly variation exists between individuals. Nevertheless, forensic gait analysis has contributed to several criminal trials in Europe in the past 15 years. The admission of gait evidence differs between courts. The methods are mainly observer-based: multiple gait analysts (independently) assess gait features on video footage of a perpetrator and suspect. Using gait feature databases, likelihood ratios of the hypotheses that the observed individuals have the same or another identity can be calculated. Automated gait recognition algorithms calculate a difference measure between video clips, which is compared with a threshold value derived from a video gait recognition database to indicate likelihood. However, only partly automated algorithms have been used in practice. We argue that the scientific basis of forensic gait analysis is limited. However, gait feature databases enable its use in court for supportive evidence with relatively low evidential value. The recommendations made in this review are (1) to expand knowledge on inter- and intra-subject gait variabilities, discriminative strength and interdependency of gait features, method accuracies, gait feature databases and likelihood ratio estimations; (2) to compare automated and observer-based gait recognition methods; to design (3) an international standard method with known validity, reliability and proficiency tests for analysts; (4) an international standard gait feature data collection method resulting in database(s); (5) (inter)national guidelines for the admission of gait evidence in court; and (6) to decrease the risk for cognitive and contextual bias in forensic gait analysis. This is expected to improve admission of gait evidence in court and judgment of its evidential value. Several ongoing research projects focus on parts of these recommendations.

Repeatability and reproducibility of earprint acquisition.

For all forensic disciplines dealing with identification -- e.g., of glass, tool marks, fibers, faces, fingers, handwriting, speakers -- in which manual (subjective, nonautomated) processes play a role, operator dependencies are relevant. With respect to earprint identification, in the period 2002-2005, the Forensic Ear Identification research project collected a database of 1229 donors, three prints per ear, and laid down a "best practice" for print acquisition. Repeatability and reproducibility aspects of the print acquisition are tested. The study suggests that different operators may acquire prints of differing quality, with equal error rates of the matching system ranging from 9% to 19%. Moreover, it turns out that "matching" earprints are more alike when taken in a consecutive row than when taken on separate occasions. This underlines the importance of (1) studying operator effects, (2) operator training, and (3) not gathering "matching" reference material at the same occasion.

Performance of the FearID earprint identification system.

The Forensic Ear Identification (FearID) research project was started in order to study the strength of evidence of earprints found on crime scenes. For this purpose, a sample of earprints from 1229 donors over three countries was collected. From each donor three left and three right earprints were gathered. On the one hand, operators denoted contours of the earprints to facilitate segmentation of the images, on the other anthropological specialists denoted anatomically specific locations. On the basis of this, methods for automated classification were developed and used for training of a system that classifies pairs of prints as 'matching' or 'non-matching'. Comparing lab quality prints, the system has an equal error rate of 4%. Starting from a reference database containing two prints per ear, hitlist behaviour is such that in 90% of all query searches the best hit is in the top 0.1% of the list. The results become less favourable (equal error rate of 9%) for print/mark comparisons.

2D/3D image (facial) comparison using camera matching.

A problem in forensic facial comparison of images of perpetrators and suspects is that distances between fixed anatomical points in the face, which form a good starting point for objective, anthropometric comparison, vary strongly according to the position and orientation of the camera. In case of a cooperating suspect, a 3D image may be taken using e.g. a laser scanning device. By projecting the 3D image onto a 2D image with the suspect's head in the same pose as that of the perpetrator, using the same focal length and pixel aspect ratio, numerical comparison of (ratios of) distances between fixed points becomes feasible. An experiment was performed in which, starting from two 3D scans and one 2D image of two colleagues, male and female, and using seven fixed anatomical locations in the face, comparisons were made for the matching and non-matching case. Using this method, the non-matching pair cannot be distinguished from the matching pair of faces. Facial expression and resolution of images were all more or less optimal, and the results of the study are not encouraging for the use of anthropometric arguments in the identification process. More research needs to be done though on larger sets of facial comparisons.

Interoperator test for anatomical annotation of earprints.

As part of the Forensic Ear Identification (FearID) research project, which aims to obtain estimators for the strength of evidence of earmarks found on crime scenes, a large database of earprints (over 1200 donors) has been collected. Starting from a knowledge-based approach where experts add anatomical annotations of minutiae and landmarks present in prints, comparison of pairs of prints is done using the method of Vector Template Matching (VTM). As the annotation process is subjective, a validation experiment was performed to study its stability. Comparing prints on the basis of VTM, it appears that there are interoperator effects, individual operators yielding significantly more consistent results when annotating prints than different operators. The operators being well trained and educated, the observed variation on both clicking frequency and choice of annotation points suggests that implementation of the above is not the best way to go about objectifying earprint comparison. Processes like the above are relevant for any forensic science dealing with identification (e.g., of glass, tool marks, fibers, faces, fingers, handwriting, speakers) where manual (nonautomated) processes play a role. In these cases, results may be operator dependent and the dependencies need to be studied.

Comparison of quantification of histochemical staining by hue-saturation-intensity (HSI) transformation and color-deconvolution.

We tested a recently developed flexible method of separation and quantification of immunohistochemical staining by means of color image analysis. An algorithm was recently developed to deconvolve the color information acquired with RGB cameras, to calculate the contribution of each of the applied stains, based on the stain-specific RGB absorption. The algorithm was tested using a set of lung-tumor samples labeled for the detection of Ki-67, an antigen expressed in proliferating cells, covering a wide range of staining levels. Quantification of the labeling was compared with HSI-based segmentation and manual analysis of the same samples. The recently developed deconvolution method performed significantly better than the HSI based system when compared to manual counting as gold standard. The deconvolution system showed significantly reduced variability in the LI determination, especially of highly labeled control samples. This resulted in significant increase in sensitivity of classification of samples with increased KI-67 labeling without changing the specificity, when compared to the HSI based method.

Amplification/overexpression of a mitotic kinase gene in human bladder cancer.

BACKGROUND: The mitotic kinase-encoding gene STK15/BTAK/ AuroraA is associated with aneuploidy and transformation when overexpressed in mammalian cells. STK15 overexpression activates an unknown oncogenic pathway that involves centrosome amplification and results in missegregation of chromosomes. Because clinical prognosis and tumor aneuploidy are tightly linked in human bladder cancer, we examined whether increased STK15 copy number and protein levels are linked to aneuploidy in bladder cancers. METHODS: STK15 protein was visualized by immunohistochemistry in 205 formalin-fixed, paraffin-embedded human bladder tumors. STK15 gene copy number was evaluated in 61 tumors by Southern blot hybridization and in 21 of these 61 tumors by fluorescence in situ hybridization (FISH). Copy numbers of chromosomes 3, 17, 20, and 21 were evaluated by FISH with chromosome-specific probes. STK15 expression levels were related to histologic grade, stage, and DNA ploidy of the tumors and to the patients' follow-up data. The chi-square test for association was used to analyze the relationship between STK15 expression and pathologic features. All statistical tests were two-sided. RESULTS: Tumors with low levels of STK15 amplification (3-4 copies) showed minimal deviation in their chromosome copy number and diploid or near-diploid total nuclear DNA content. Tumors with higher levels of STK15 amplification (>4 copies) had a major increase of chromosome copy number and of their total nuclear DNA content, i.e., exhibited pronounced aneuploidy. Elevated expression of STK15 was strongly associated with parameters of clinical aggressiveness including high histologic grade (P<.001), invasion (P<.001), increased rate of metastasis (P<.001), and decreased metastasis-free (P<.001) and overall (P<.001) survival of patients with bladder cancer. CONCLUSION: STK15 gene amplification and associated increased expression of the mitotic kinase it encodes are associated with aneuploidy and aggressive clinical behavior in human bladder cancer.

Hepatocytes and epithelial cells of donor origin in recipients of peripheral-blood stem cells.

BACKGROUND: Bone marrow contains stem cells with the potential to differentiate into mature cells of various organs. We determined whether circulating stem cells have a similar potential. METHODS: Biopsy specimens from the liver, gastrointestinal tract, and skin were obtained from 12 patients who had undergone transplantation of hematopoietic stem cells from peripheral blood (11 patients) or bone marrow (1 patient). Six female patients had received transplants from a male donor. Five had received a sex-matched transplant, and one had received an autologous transplant. Hematopoietic stem-cell engraftment was verified by cytogenetic analysis or restriction-fragment--length polymorphism analysis. The biopsies were studied for the presence of donor-derived epithelial cells or hepatocytes with the use of fluorescence in situ hybridization of interphase nuclei and immunohistochemical staining for cytokeratin, CD45 (leukocyte common antigen), and a hepatocyte-specific antigen. RESULTS: All six recipients of sex-mismatched transplants showed evidence of complete hematopoietic donor chimerism. XY-positive epithelial cells or hepatocytes accounted for 0 to 7 percent of the cells in histologic sections of the biopsy specimens. These cells were detected in liver tissue as early as day 13 and in skin tissue as late as day 354 after the transplantation of peripheral-blood stem cells. The presence of donor cells in the biopsy specimens did not seem to depend on the intensity of tissue damage induced by graft-versus-host disease. CONCLUSIONS: Circulating stem cells can differentiate into mature hepatocytes and epithelial cells of the skin and gastrointestinal tract.