Is this the true face of Anne Boleyn? — BBC News

[0:02] When I started looking into this story, I thought it was going to be a simple one. [0:07] Then this happened. [0:09] The result has shocked us completely. [0:12] Has facial recognition discovered a hidden portrait of Anne Boleyn, wife of Henry VIII? [0:16] I'm afraid to say it, but I think it's a load of rubbish. [0:19] Is this traditionally recognised portrait of the Tudor queen actually her mum instead? [0:25] I don't get mocked up. Just results are results, isn't it? [0:28] To really understand our fascination with this Tudor queen and what she looked like, [0:35] I've come to London to visit the National Portrait Gallery. [0:44] Welcome to the Tudor Gallery. [0:46] Wow, look at this. [0:47] So I think it's fair to say that Anne Boleyn is one of the most famous figures from English history. [0:52] So she is Henry VIII's second wife. [0:54] And I'm just looking because obviously her husband is there. [0:58] You wouldn't want to mess with him, would you? [1:00] He ultimately divorced Catherine of Aragon, breaking England from the church in Rome [1:04] for Henry to then marry Anne Boleyn. [1:06] So she triumphed, became Queen of England. [1:09] There's their baby who became Queen Elizabeth I, right? [1:13] Exactly. [1:14] But then after only three years, court kind of conspired against her, [1:18] her own mistakes, her own actions, and she ended up being executed on the scaffold at the Tower of London. [1:24] We know this painting was made in the late 16th century, i.e. long after Anne's death. [1:29] So how would they know what she looked like? [1:31] Well, this is the kind of conundrum of the many mysteries that surround Anne Boleyn. [1:36] One of them is the fact that we don't have a lifetime painted portrait of her that's kind of [1:41] absolutely secure, a kind of a wonderful painting that we can use as a reference point [1:46] to tell all those stories about her. [1:48] Her reign wasn't necessarily long enough for a kind of established iconography. [1:52] And there is this kind of tantalising suggestion that perhaps some of her images might have been [1:57] deliberately destroyed. [2:00] And we've been fascinated with what she looked like ever since. [2:08] So could computer science reveal what Anne Boleyn actually looked like during her lifetime? [2:14] More recently, we've got a lot more powerful facial recognition systems. [2:18] If evidence can be tested, then it should be tested. [2:21] Facial recognition allows computers to identify or verify someone from their face. [2:28] The technology isn't without controversy. [2:30] It's used for things like unlocking your phone, [2:33] passport control and some police investigations. [2:37] But what about using facial recognition on sketches from the past? [2:41] An objective tool like this can be used to actually answer quite a lot of interesting and unknown questions. [2:48] Even though there are no known paintings of Anne Boleyn made during her lifetime, [2:54] there are a few depictions, including this sketch by Hans Holbein the Younger. [3:02] It is considered by many modern historians to be a genuine preparatory sketch of her. [3:07] So she would have had to sit for this sketch, giving us a close likeness. [3:11] Except for the questions. [3:14] The age of the lettering, it's not in a Tudor style but likely an 18th century hand. [3:20] The light coloured hair when she was thought to be dark haired. [3:23] The full chin when accounts suggest a slender neck. [3:27] And her informal dress on a queen. [3:30] And there are of course arguments to counter these, more on those later. [3:34] A team led by the University of Bradford has used facial recognition on the digital copies of the [3:40] whole collection of drawings that this one belongs to, to see if an algorithm can put to bed the debate. [3:47] So the algorithm has been trained on photos of people. [3:51] What we are looking at is a bunch of drawings and then we are comparing these drawings through a [3:57] machine-learned algorithm where there's no human input. [4:02] What we have done here is we have compared these drawings to Anne Boleyn's first cousins and to [4:08] her daughter Elizabeth to look for the family similarity and geometry and they cluster. [4:16] And we have used drawings that we absolutely know are non-relations and they don't cluster. [4:23] They have interpreted the percentages and clustering where images group together based on facial resemblance [4:29] to propose a new theory. This drawing is more likely to be Anne Boleyn's mum. [4:35] And this previously unidentified woman could in fact be the doomed queen. [4:40] I think it's very exciting we are opening new doors. [4:43] To generate leads in art history you know where the evidence is fragmentary and historians face a momentous [4:51] task. Case solved then? Not so fast. [4:56] A lot of art historical colleagues are a bit nervous about this kind of sort of [5:00] gloves off stuff but I think you know if you see it you've got to say it. Why not? [5:04] I think academically I would describe it as a load of old phooey. [5:08] I think this is trying to treat works of art as modern photographs and it's simply impossible to do [5:14] that. That's before you get into any of the other problems about their methodology and how they've [5:19] approached this whole question. First of all the drawing that we have for a long time thought was Anne Boleyn, [5:25] has her name on the top left hand corner. It says Anne Boleyn Queen. [5:29] And we know that that identification came from someone who knew what Anne Boleyn looked like. [5:33] To attempt to demolish that with the aid of computer science 500 years after the event I think is [5:41] suspicious. But I also think it's suspicious that they then say that another completely unrelated [5:46] drawing which no one has ever said is Anne Boleyn before is in fact Anne Boleyn. I think one of the [5:52] things that convinces me that this drawing is in fact Anne Boleyn is that she's shown in a very [5:57] informal pose and it sounds paradoxical to say it but actually a queen would be more likely to be [6:05] seen at court in this kind of private dress. For much of the period she was queen Anne Boleyn was [6:10] pregnant so I think it makes perfect sense that this is recording her in that moment. [6:15] So where does this leave us? It's important that you know this work and the result of it isn't [6:23] about replacing scholarship or this is definitively Anne. It's not the end of a conversation it's the [6:31] beginning of a conversation. So this is just another tool I think that will help the people who are [6:37] working in this field especially art historians. The incredible emotional tragedy ultimately of her life [6:44] is this story that people want to revisit. She's a subject in which people are so fascinated that [6:48] there is this curiosity and I think that kind of drives sort of ongoing research. People throwing [6:53] different methodologies to try and answer a question that has been thought about for hundreds of years.