\u201cDo you think that every fingerprint is actually unique?\u201d <\/p>\n
It\u2019s a question that a professor asked Gabe Guo during a casual chat while he was stuck at home during the Covid-19 lockdowns, waiting to start his freshman year at Columbia University. \u201cLittle did I know that conversation would set the stage for the focus of my life for the next three years,\u201d Guo said. <\/p>\n
Guo, now an undergraduate senior in Columbia\u2019s department of computer science, led a team that did a study on the subject, with the professor, Wenyao Xu of the University of Buffalo, as one of his coauthors. Published this week\u00a0in the journal Science Advances, the paper seemingly upends a long-accepted truth about fingerprints: They are not, Guo and his colleagues argue, all unique. <\/p>\n
In fact, journals rejected the work multiple times before the team appealed and eventually got it accepted at Science Advances. \u201cThere was a lot of pushback from the forensics community initially,\u201d recalled Guo, who had no background in forensics before the study. <\/p>\n
\u201cFor the first iteration or two of our paper, they said it\u2019s a well-known fact that no two fingerprints are alike. I guess that really helped to improve our study, because we just kept putting more data into it, (increasing accuracy) until eventually the evidence was incontrovertible,\u201d he said. <\/p>\n
To get to its surprising results, the team employed an artificial intelligence model called a deep contrastive network, which is commonly used for tasks such as facial recognition. The researchers added their own twist to it and then fed it a US government database of 60,000 fingerprints in pairs that sometimes belonged to the same person (but from different fingers) and sometimes belonged to different people. <\/p>\n
As it worked, the AI-based system found that fingerprints from different fingers of the same person shared strong similarities and was therefore able to tell when the fingerprints belonged to the same individual and when they didn\u2019t, with an accuracy for a single pair peaking at 77% \u2014 seemingly disproving that each fingerprint is \u201cunique.\u201d <\/p>\n
\u201cWe found a rigorous explanation for why this is the case: the angles and curvatures at the center of the fingerprint,\u201d Guo said. <\/p>\n
For hundreds of years of forensic analysis, he added, people have been looking at different features called \u201cminutiae,\u201d the branchings and endpoints in fingerprint ridges that are used as the traditional markers for fingerprint identification. \u201cThey are great for fingerprint matching, but not reliable for finding correlations among fingerprints from the same person,\u201d Guo said. \u201cAnd that\u2019s the insight we had.\u201d <\/p>\n
The authors said they are aware of potential biases in the data. Although they believe the AI system operates in much the same way across genders and races, for the system to be usable in actual forensics, more careful validation is required through the analysis of a larger and broader database of fingerprints, according to the study. <\/p>\n
However, Guo said he\u2019s confident that the discovery can improve criminal investigations.: <\/p>\n
\u201cThe most immediate application is it can help generate new leads for cold cases, where the fingerprints left at the crime scene are from different fingers than those on file,\u201d he said. \u201cBut on the flip side, this won\u2019t just help catch more criminals. This will also actually help innocent people who might not have to be unnecessarily investigated anymore. And I think that\u2019s a win for society.\u201d <\/p>\n
Using deep learning techniques on fingerprint images is an interesting topic, according to Christophe Champod, a professor of forensic science at the School of Criminal Justice of the University of Lausanne in Switzerland. However, Champod, who wasn\u2019t involved in the study, said he doesn\u2019t believe the work has uncovered anything new. <\/p>\n
\u201cTheir argument that these shapes are somewhat correlated between fingers has been known from the early start of fingerprinting, when it was done manually, and it has been documented for years,\u201d he said. \u201cI think they have oversold their paper, by lack of knowledge, in my view. I\u2019m happy that they have rediscovered something known, but essentially, it\u2019s a tempest in a teacup.\u201d <\/p>\n
In response, Guo said that nobody had ever systematically quantified or used the similarities between fingerprints from different fingers of the same person to the degree that the new study has. <\/p>\n
\u201cWe are the first to explicitly point out that the similarity is due to the ridge orientation at the center of the fingerprint,\u201d Guo said. \u201cFurthermore, we are the first to attempt to match fingerprints from different fingers of the same person, at least with an automated system.\u201d <\/p>\n
Simon Cole, a professor in the department of criminology, law and society at the University of California, Irvine, agreed that the paper is interesting but said its practical utility is overstated. Cole was also not involved in the study. <\/p>\n
\u201cWe were not \u2018wrong\u2019 about fingerprints,\u201d he said of forensic experts. \u201cThe unproven but intuitively true claim that no two fingerprints are \u2018exactly alike\u2019 is not rebutted by finding that fingerprints are similar. Fingerprints from different people, as well as from the same person have always been known to be similar.\u201d <\/p>\n
The paper said the system could be useful in crime scenes in which the fingerprints found are from different fingers than those in the police record, but Cole said that this can only occur in rare cases, because when prints are taken, all 10 fingers and often palms are routinely recorded. \u201cIt\u2019s not clear to me when they think law enforcement will have only some, but not all, of an individual\u2019s fingerprints on record,\u201d he said. <\/p>\n
The team behind the study says it\u2019s confident in the results and has open-sourced the AI code for others to check, a decision both Champod and Cole praised. But Guo said the importance of the study goes beyond fingerprints. <\/p>\n
\u201cThis isn\u2019t just about forensics, it\u2019s about AI. Humans have been looking at fingerprints since we existed, but nobody ever noticed this similarity until we had our AI analyze it. That just speaks to the power of AI to automatically recognize and extract relevant features,\u201d he said. <\/p>\n
\u201cI think this study is just the first domino in a huge sequence of these things. We\u2019re going to see people using AI to discover things that were literally hiding in plain sight, right in front of our eyes, like our fingers.\u201d <\/p>\n\n
\u201cDo you think that every fingerprint is actually unique?\u201d It\u2019s a question that a professor asked Gabe Guo during a casual chat while he was stuck at home during the Covid-19 lockdowns, waiting to start his freshman year at Columbia University. \u201cLittle did I know that conversation would set the stage for the focus of <\/p>\n","protected":false},"author":0,"featured_media":13965,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[23],"tags":[],"class_list":{"0":"post-13964","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-world"},"_links":{"self":[{"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/posts\/13964","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/comments?post=13964"}],"version-history":[{"count":0,"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/posts\/13964\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/media\/13965"}],"wp:attachment":[{"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/media?parent=13964"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/categories?post=13964"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/shareperformanceinsight.com\/index.php\/wp-json\/wp\/v2\/tags?post=13964"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}