1 00:00:09,093 --> 00:00:12,693 Speaker 1: You're listening to a podcast from News Talk ZEDB. Follow 2 00:00:12,773 --> 00:00:16,133 Speaker 1: this and our wide range of podcasts now on iHeartRadio. 3 00:00:16,853 --> 00:00:19,452 Speaker 2: Justice Minister Paul Goldsmith wants to allow the use of 4 00:00:19,493 --> 00:00:23,093 Speaker 2: facial recognition technology in the fight against retail crime, despite 5 00:00:23,133 --> 00:00:27,013 Speaker 2: acknowledging tensions with people's right to privacy. To discuss this, 6 00:00:27,133 --> 00:00:30,373 Speaker 2: it's great to have Retail n Z Chief executive Carolyn 7 00:00:30,693 --> 00:00:33,253 Speaker 2: Young on the phone. Carolyn, very good afternoon to you. 8 00:00:34,293 --> 00:00:35,253 Speaker 3: Carol, A good afternoon. 9 00:00:35,693 --> 00:00:39,452 Speaker 4: So how does this trial facial recognition technology work in 10 00:00:39,493 --> 00:00:39,973 Speaker 4: a store? 11 00:00:42,053 --> 00:00:44,973 Speaker 3: Well, it's I'll do my best to describe it and 12 00:00:45,013 --> 00:00:48,293 Speaker 3: a quick couplement. It's as quite complex system. So basically 13 00:00:49,053 --> 00:00:52,413 Speaker 3: to want to put a facial recognition trial in your store, 14 00:00:52,452 --> 00:00:54,413 Speaker 3: you need to have some reason why you would do that. 15 00:00:54,613 --> 00:00:57,013 Speaker 3: So that would be because you've got a number of 16 00:00:57,093 --> 00:01:02,773 Speaker 3: people that are continuing to cause abuse and violence and 17 00:01:02,813 --> 00:01:05,933 Speaker 3: aggression in store. The primary reason it's been put on 18 00:01:06,053 --> 00:01:09,493 Speaker 3: faces for staff safety. A lot of violent and aggressive 19 00:01:09,533 --> 00:01:13,893 Speaker 3: behavior we see in retail these days, and so what 20 00:01:14,613 --> 00:01:17,453 Speaker 3: stores have what food Stuffs have done, and they've established 21 00:01:17,533 --> 00:01:22,773 Speaker 3: in a number of stores people that have offended in store, 22 00:01:22,813 --> 00:01:26,373 Speaker 3: whether it's that they have been aggressive and violent towards staff, 23 00:01:26,493 --> 00:01:29,173 Speaker 3: or potentially they may have stolen and been aggressive and 24 00:01:29,212 --> 00:01:32,572 Speaker 3: those sorts of behaviors. They've trespassed them, they've ben offended. 25 00:01:32,613 --> 00:01:35,853 Speaker 3: They've got a photo of them from the truspass. Notice. 26 00:01:36,493 --> 00:01:40,853 Speaker 3: They load that photo and the photo is a headshot only, 27 00:01:40,932 --> 00:01:44,732 Speaker 3: so it doesn't include anything below your chin, so no shoulders, 28 00:01:44,773 --> 00:01:47,573 Speaker 3: no body, no nothing, It's only your head. And so 29 00:01:47,653 --> 00:01:52,532 Speaker 3: the headshot gets loaded into the facial resgnition technology system. 30 00:01:52,893 --> 00:01:56,253 Speaker 3: And in the stores that they were random stores that 31 00:01:56,293 --> 00:01:58,773 Speaker 3: were selected to do the trial as part of the 32 00:01:58,813 --> 00:02:02,493 Speaker 3: requirements from the Privacy Commissioner, And in those twenty five 33 00:02:02,573 --> 00:02:06,053 Speaker 3: stores that did the trial, they had large signs out 34 00:02:06,053 --> 00:02:10,053 Speaker 3: the front of the store at every entrance telling people 35 00:02:10,093 --> 00:02:13,013 Speaker 3: that they had that their fatal recognition was in play 36 00:02:13,053 --> 00:02:14,973 Speaker 3: in the store, and that if they didn't want to 37 00:02:15,013 --> 00:02:18,173 Speaker 3: come in store, that was their obviously their ability to 38 00:02:18,252 --> 00:02:20,373 Speaker 3: not come in, but they were notified before they entered 39 00:02:20,413 --> 00:02:22,773 Speaker 3: store so that they had the choice about whether they 40 00:02:22,813 --> 00:02:25,293 Speaker 3: came in the store. When you walk in the store, 41 00:02:25,333 --> 00:02:28,213 Speaker 3: and you or I walk in, we have never offended 42 00:02:28,532 --> 00:02:34,373 Speaker 3: in that particular store, our image is deleted immediately. There's 43 00:02:34,413 --> 00:02:38,613 Speaker 3: no storing of any data if, on the other hand, 44 00:02:38,733 --> 00:02:41,532 Speaker 3: John Smith, who last time he was in the store 45 00:02:41,613 --> 00:02:48,773 Speaker 3: he spat and kicked that star. Yeah, he has loaded 46 00:02:48,813 --> 00:02:50,933 Speaker 3: up into the system. He comes back into store after 47 00:02:51,053 --> 00:02:56,053 Speaker 3: he's been trespassed, an alert goes to a device that 48 00:02:56,213 --> 00:03:00,733 Speaker 3: tells the store that John Smith has just entered. Now 49 00:03:00,773 --> 00:03:04,053 Speaker 3: there's a couple of things that happened here. Firstly, the 50 00:03:04,093 --> 00:03:07,413 Speaker 3: store can traffic lighter a person that they enter in, 51 00:03:07,453 --> 00:03:11,133 Speaker 3: so they might actually like someone to say, really violent 52 00:03:11,213 --> 00:03:14,693 Speaker 3: and aggressive, do not approach, call the police immediately. You know, 53 00:03:14,773 --> 00:03:17,933 Speaker 3: based on the previous actions that this person has had 54 00:03:18,093 --> 00:03:23,252 Speaker 3: in that store, and so you would know. And part 55 00:03:23,293 --> 00:03:25,653 Speaker 3: of the way you create a safer work environment is 56 00:03:25,693 --> 00:03:28,093 Speaker 3: that you would then know that you've got an extremely 57 00:03:28,173 --> 00:03:30,773 Speaker 3: violent and aggressive person in store, and he's not to 58 00:03:30,773 --> 00:03:33,693 Speaker 3: be he or she is not to be approached. You 59 00:03:33,773 --> 00:03:37,413 Speaker 3: might have somebody else who is, you know, maybe they 60 00:03:37,413 --> 00:03:40,413 Speaker 3: had a bad day, they haven't offended previously, they were 61 00:03:40,453 --> 00:03:43,293 Speaker 3: abusive in store, but they have been trespassed for three 62 00:03:43,333 --> 00:03:47,013 Speaker 3: months or something like that, so they might well be approachable. 63 00:03:47,093 --> 00:03:50,732 Speaker 3: So you could easily approach them as they have come 64 00:03:50,853 --> 00:03:53,293 Speaker 3: to start to have come in the store and say, 65 00:03:53,293 --> 00:03:56,453 Speaker 3: excuse me, John Smith will use John Smith again, Well, 66 00:03:56,493 --> 00:03:58,853 Speaker 3: maybe you'll use free dag. Excuse me, free dag. But 67 00:03:58,893 --> 00:04:00,693 Speaker 3: you know you've been trespassed. You're not meant to be 68 00:04:00,733 --> 00:04:03,893 Speaker 3: in here. And you know eighty to ninety percent of 69 00:04:03,933 --> 00:04:09,173 Speaker 3: the times you approach somebody upon entry and acknowledge them around, 70 00:04:09,293 --> 00:04:11,853 Speaker 3: the actions are taken previously and they shouldn't be in stored. 71 00:04:11,893 --> 00:04:15,613 Speaker 3: They will turn around and walk out and they apologize, 72 00:04:16,533 --> 00:04:18,653 Speaker 3: and then there might be some other people that you 73 00:04:18,813 --> 00:04:22,772 Speaker 3: might just monitor in store. And what facial recognition does 74 00:04:23,173 --> 00:04:27,253 Speaker 3: is that it's a biometric that it takes a view 75 00:04:27,333 --> 00:04:30,893 Speaker 3: of the face that matches up your facial features. The 76 00:04:31,133 --> 00:04:35,653 Speaker 3: minimum match was set at ninety percent, and what food 77 00:04:35,693 --> 00:04:38,373 Speaker 3: Stuff's recognized is that the quality of the photo you 78 00:04:38,373 --> 00:04:40,413 Speaker 3: put into the system needs to be quite high to 79 00:04:40,533 --> 00:04:44,053 Speaker 3: ensure that you get an accurate match. So the threshold 80 00:04:44,173 --> 00:04:47,573 Speaker 3: was ninety percent. If anything was over ninety four or 81 00:04:47,653 --> 00:04:50,373 Speaker 3: ninety five percent, they knew that virtually every time it 82 00:04:50,453 --> 00:04:53,973 Speaker 3: was one hundred percent match between ninety and ninety four 83 00:04:53,973 --> 00:04:56,053 Speaker 3: percent has to take more care because there is an 84 00:04:56,053 --> 00:04:59,613 Speaker 3: element of risk in there, and so with every alert 85 00:04:59,653 --> 00:05:02,813 Speaker 3: that they get, they'd have two trained people would look 86 00:05:02,853 --> 00:05:06,373 Speaker 3: at that photo and consider whether or not it was 87 00:05:06,413 --> 00:05:08,813 Speaker 3: the person that was in their system. 88 00:05:09,293 --> 00:05:12,253 Speaker 4: So when going going forward with this situation, you say, 89 00:05:12,253 --> 00:05:14,573 Speaker 4: this was just sort of people splitting and violent offenders 90 00:05:14,573 --> 00:05:18,853 Speaker 4: and starch. So shoplifters aren't the ones being targeted in 91 00:05:18,893 --> 00:05:21,853 Speaker 4: this trial. But would you see going forward that shoplifters 92 00:05:22,013 --> 00:05:26,213 Speaker 4: would have their faces loaded into this facial recognition technology? 93 00:05:27,093 --> 00:05:30,533 Speaker 3: Yeah, so shoplifters may well have also been included because 94 00:05:30,573 --> 00:05:33,733 Speaker 3: people that are feeling are often violent and aggressive. What's that? 95 00:05:34,453 --> 00:05:37,653 Speaker 3: So there's a combination of things that the primary reason 96 00:05:37,813 --> 00:05:41,933 Speaker 3: was to keep the staff safe, and by understanding who's 97 00:05:41,933 --> 00:05:44,933 Speaker 3: in the store enables you to create a safer work 98 00:05:45,013 --> 00:05:50,213 Speaker 3: environment for your staff and for your customers. So it ultimately, 99 00:05:50,573 --> 00:05:53,173 Speaker 3: you know, does a dual purpose, right, It will make 100 00:05:53,213 --> 00:05:56,613 Speaker 3: the store safer and will reduce the amount offending because 101 00:05:56,653 --> 00:06:00,813 Speaker 3: most of the people that are being violent and abusive 102 00:06:01,453 --> 00:06:05,493 Speaker 3: and aggressive are also offending to a certain degree in store. 103 00:06:05,773 --> 00:06:08,253 Speaker 3: I mean, you can't go and say to your work calling, 104 00:06:08,373 --> 00:06:10,293 Speaker 3: you can't go and split at the nose or punch 105 00:06:10,373 --> 00:06:13,893 Speaker 3: them off. And videos of a four second interaction between 106 00:06:13,893 --> 00:06:16,413 Speaker 3: a customer and a staff member where the customer just 107 00:06:16,493 --> 00:06:19,693 Speaker 3: punches the staff member in the face and it's got 108 00:06:19,773 --> 00:06:22,413 Speaker 3: accelerated in four seconds. They walk up to the counter, 109 00:06:22,493 --> 00:06:25,613 Speaker 3: they have a conversation, they smack them straight away. I've 110 00:06:25,653 --> 00:06:30,333 Speaker 3: seen other images where people's gone in store and they 111 00:06:30,373 --> 00:06:33,013 Speaker 3: have set fire. They've done us in a store to 112 00:06:33,053 --> 00:06:35,653 Speaker 3: steal a trolley load of gods. So they've gone in 113 00:06:35,693 --> 00:06:38,693 Speaker 3: there and that puts every staff member in danger. Right, 114 00:06:38,733 --> 00:06:42,533 Speaker 3: if your business is going to be set alight, that 115 00:06:42,733 --> 00:06:45,613 Speaker 3: is quite stressful environment to be in, so you don't 116 00:06:45,693 --> 00:06:48,333 Speaker 3: want to help the host people coming back in your store, 117 00:06:48,333 --> 00:06:51,693 Speaker 3: and you want to protect yourself. So it's a dual purpose, right, 118 00:06:51,733 --> 00:06:54,653 Speaker 3: it protects The primary thing is that it protects the 119 00:06:54,693 --> 00:06:57,613 Speaker 3: staff and creates a safe environment. But at the same time, 120 00:06:57,693 --> 00:07:00,693 Speaker 3: these are people that are offending, so it will reduce 121 00:07:00,733 --> 00:07:02,973 Speaker 3: the level of crime, and it can be used as 122 00:07:02,973 --> 00:07:07,293 Speaker 3: a preventative tool rather than a reactive tool after the event. 123 00:07:07,693 --> 00:07:09,813 Speaker 3: And a key thing is that if you can approach 124 00:07:09,853 --> 00:07:13,013 Speaker 3: someone within the first minute of them being in the store, 125 00:07:13,733 --> 00:07:16,493 Speaker 3: they have not got themselves worked up into a frenzy 126 00:07:16,533 --> 00:07:18,413 Speaker 3: and they're not going to be as aggresive and violent 127 00:07:18,573 --> 00:07:20,933 Speaker 3: as you are. If you get them straight away, if 128 00:07:20,933 --> 00:07:22,973 Speaker 3: they've had time to mooch around the store and they 129 00:07:23,013 --> 00:07:25,253 Speaker 3: know that they've got to get your adrenaline up to 130 00:07:25,293 --> 00:07:27,613 Speaker 3: force through a trolley worth of goods and not pay 131 00:07:27,693 --> 00:07:30,413 Speaker 3: for it. If you're doing that before they've even got 132 00:07:30,493 --> 00:07:33,373 Speaker 3: anything in a trolley or in a bag, you get 133 00:07:33,413 --> 00:07:35,853 Speaker 3: a much better outcome and certainly the outcomes and the 134 00:07:35,893 --> 00:07:38,613 Speaker 3: trials for that time and time again, we're. 135 00:07:38,493 --> 00:07:42,093 Speaker 4: Talking to Carolyn Young, Retail New Zealand Chief Executive. So 136 00:07:42,333 --> 00:07:45,813 Speaker 4: is it security that approaches the people? So you have 137 00:07:46,493 --> 00:07:50,853 Speaker 4: security guards on staff and they approach them. It's not 138 00:07:50,933 --> 00:07:53,053 Speaker 4: up to the checkout person to approach these people that 139 00:07:53,053 --> 00:07:53,373 Speaker 4: are ping. 140 00:07:54,293 --> 00:07:56,173 Speaker 3: Well, no, it's not up to the checkout person. So 141 00:07:56,573 --> 00:07:59,893 Speaker 3: it'll be people in store that have been identified and 142 00:07:59,973 --> 00:08:02,893 Speaker 3: have been trained. So it could be a security guard 143 00:08:02,933 --> 00:08:04,933 Speaker 3: if there's no security guard on judy, because it's not 144 00:08:04,973 --> 00:08:07,213 Speaker 3: there's two people. So you'll probably have three or four 145 00:08:07,253 --> 00:08:10,493 Speaker 3: people across environment of a supermarket that are trained at 146 00:08:10,533 --> 00:08:13,973 Speaker 3: any point in time that could do the identification and 147 00:08:14,013 --> 00:08:17,293 Speaker 3: would get better alert So, for example, if it's at 148 00:08:17,293 --> 00:08:19,733 Speaker 3: a time when a security guard isn't on duty, then 149 00:08:19,773 --> 00:08:22,173 Speaker 3: it would be it'll be two other senior people within 150 00:08:22,213 --> 00:08:24,733 Speaker 3: the store, but it wouldn't be a checkout operator that 151 00:08:24,733 --> 00:08:27,373 Speaker 3: would be asked to ask someone to leave. It's someone 152 00:08:27,413 --> 00:08:30,493 Speaker 3: that's trained and skilled and doing so and can identify, 153 00:08:31,013 --> 00:08:34,853 Speaker 3: you know, as this person violent and aggressive and do 154 00:08:34,893 --> 00:08:36,653 Speaker 3: we need to call a police straight away? And that's 155 00:08:36,653 --> 00:08:39,133 Speaker 3: a really that's probably one of the greatest tools is 156 00:08:39,173 --> 00:08:42,533 Speaker 3: knowing that people that are really aggressive can be addressed 157 00:08:42,533 --> 00:08:44,333 Speaker 3: in a way in which you don't have to you 158 00:08:44,372 --> 00:08:46,773 Speaker 3: call the police. They will come because they know that 159 00:08:46,773 --> 00:08:51,012 Speaker 3: you've already identified someone that's been high level offending previously. 160 00:08:51,293 --> 00:08:53,652 Speaker 2: What are the laws in place for the storage of 161 00:08:53,732 --> 00:08:56,013 Speaker 2: that data, caront because a lot of people they may 162 00:08:56,372 --> 00:08:59,093 Speaker 2: unfairly be freaking out they come to upt images of 163 00:08:59,213 --> 00:09:03,413 Speaker 2: Minority Report nineteen eighty four. But as the strict laws 164 00:09:03,533 --> 00:09:06,772 Speaker 2: and fail safes in place that that data is deleted, 165 00:09:06,813 --> 00:09:09,653 Speaker 2: as you say, if nobody does anything wrong and certainly 166 00:09:09,732 --> 00:09:11,173 Speaker 2: can't get into the wrong hands. 167 00:09:11,732 --> 00:09:14,372 Speaker 3: Yeah, so there's a couple of things. I guess, well, 168 00:09:14,372 --> 00:09:16,453 Speaker 3: there's quite a lot of things not try and remember 169 00:09:16,453 --> 00:09:20,252 Speaker 3: to cover everything off. But firstly, for those people that 170 00:09:20,533 --> 00:09:23,853 Speaker 3: are not on the alert list, your images to meet 171 00:09:24,053 --> 00:09:26,533 Speaker 3: deleted immediately because there's nothing to match against. So within 172 00:09:26,573 --> 00:09:29,173 Speaker 3: the second of you being in the store, your image 173 00:09:29,173 --> 00:09:33,573 Speaker 3: is deleted. The person who has created the alert or 174 00:09:33,573 --> 00:09:38,093 Speaker 3: the image that's created the alert, that file is deleted 175 00:09:38,093 --> 00:09:40,653 Speaker 3: at midnight that night. This is how the trial was 176 00:09:40,653 --> 00:09:44,012 Speaker 3: a set up with the privacy commissioner. So that means 177 00:09:44,053 --> 00:09:48,413 Speaker 3: that the store has got till midnight to complete a 178 00:09:48,773 --> 00:09:52,053 Speaker 3: report around what happened, was it the right person? You know, 179 00:09:52,093 --> 00:09:54,532 Speaker 3: all of those sorts of things and file that. But 180 00:09:54,573 --> 00:09:57,813 Speaker 3: then that file is then removed from the system and 181 00:09:57,852 --> 00:10:01,613 Speaker 3: that's controlled through you know, third parties that controlled all 182 00:10:01,653 --> 00:10:04,733 Speaker 3: of that stuff, so it's not stored anywhere you can't 183 00:10:04,773 --> 00:10:09,653 Speaker 3: go into. And the computer that the the financial the 184 00:10:09,653 --> 00:10:13,373 Speaker 3: facial recognition technology sits on as a separate computer. It's 185 00:10:13,413 --> 00:10:16,733 Speaker 3: not on a network, it's not on Wi Fi, it's 186 00:10:16,813 --> 00:10:21,372 Speaker 3: not on any system that is part of a supermarket 187 00:10:21,413 --> 00:10:25,813 Speaker 3: network or within the store. It's completely standalone. So and 188 00:10:26,213 --> 00:10:29,933 Speaker 3: it doesn't store anything beyond midnight of an alert from 189 00:10:30,012 --> 00:10:33,413 Speaker 3: that person. So some of those things might be tweaked 190 00:10:33,453 --> 00:10:36,373 Speaker 3: a little bit. You can imagine as an example, in 191 00:10:36,413 --> 00:10:40,213 Speaker 3: a supermarket, if you are matching a face and only 192 00:10:40,293 --> 00:10:44,372 Speaker 3: the face you and it's a ninety six percent match, 193 00:10:44,533 --> 00:10:48,093 Speaker 3: then you know that's that person come into store, very 194 00:10:48,173 --> 00:10:50,813 Speaker 3: hard to find that person on a Saturday afternoment, you've 195 00:10:50,813 --> 00:10:53,732 Speaker 3: got hundreds of people in the store because you don't 196 00:10:53,773 --> 00:10:55,653 Speaker 3: you don't have any idea what they're wearing at all. 197 00:10:57,293 --> 00:10:59,133 Speaker 3: Did you find it because all you've got from the 198 00:10:59,132 --> 00:11:01,053 Speaker 3: image as a face? Yeah? 199 00:11:01,492 --> 00:11:04,413 Speaker 4: Did you find because you said this was heavily sign 200 00:11:04,773 --> 00:11:07,652 Speaker 4: signed and signposted for people coming into the stores that 201 00:11:07,732 --> 00:11:09,573 Speaker 4: are on the trial. Did you find that it affected 202 00:11:09,653 --> 00:11:13,173 Speaker 4: numbers going in? Because that's really if people are comfortable, 203 00:11:13,213 --> 00:11:14,773 Speaker 4: if people are going in and they're happy to be 204 00:11:15,293 --> 00:11:20,533 Speaker 4: have their their faces recognized. That I mean round about 205 00:11:20,533 --> 00:11:24,053 Speaker 4: way of saying, didn't affect the business? 206 00:11:25,573 --> 00:11:27,733 Speaker 3: No, not in a negative way, not like that. No, 207 00:11:27,852 --> 00:11:30,533 Speaker 3: not at all. There's always people that will question whether 208 00:11:30,612 --> 00:11:34,373 Speaker 3: they're comfortable with something like that technology being used, and 209 00:11:34,413 --> 00:11:36,413 Speaker 3: they may choose not to go install. But there was 210 00:11:36,453 --> 00:11:40,533 Speaker 3: no absolutely less well less than one percent. And then 211 00:11:40,653 --> 00:11:43,773 Speaker 3: there's always ways in which people can access further information 212 00:11:43,892 --> 00:11:46,612 Speaker 3: via a website around how it's run and what happens 213 00:11:46,612 --> 00:11:49,013 Speaker 3: in a faq on the website and those sorts of things. 214 00:11:49,093 --> 00:11:52,132 Speaker 3: So the key is making sure that you communicate really 215 00:11:52,173 --> 00:11:55,053 Speaker 3: well and really strongly with your customers so that they're 216 00:11:55,053 --> 00:11:58,053 Speaker 3: confident when they're coming install that they're being well looked 217 00:11:58,093 --> 00:12:01,292 Speaker 3: after and that people aren't using their images in any 218 00:12:01,293 --> 00:12:02,732 Speaker 3: way that's inappropriate. 219 00:12:02,973 --> 00:12:04,852 Speaker 4: Well, just two questions to finish, Thank you so much 220 00:12:04,852 --> 00:12:08,613 Speaker 4: for your time. Will the data be shared with the 221 00:12:08,653 --> 00:12:11,853 Speaker 4: police via the Aurora network? And secondly, what about people 222 00:12:11,892 --> 00:12:14,372 Speaker 4: wearing masks and head coverings or disguises? 223 00:12:15,413 --> 00:12:18,532 Speaker 3: Great question, right, Let's let's deal with the seat of 224 00:12:18,573 --> 00:12:22,012 Speaker 3: the last question first. So what you know, especially if 225 00:12:22,012 --> 00:12:24,772 Speaker 3: you've got security sitting outside your store, if someone's coming 226 00:12:24,813 --> 00:12:28,413 Speaker 3: in with a mask, hotty up and dark glasses, that's 227 00:12:29,012 --> 00:12:34,333 Speaker 3: that's screams and cat leaders travel right, telltale signs, and 228 00:12:34,372 --> 00:12:38,292 Speaker 3: so what normally happens. The social recognition system normally has 229 00:12:38,612 --> 00:12:42,813 Speaker 3: between two and four cameras in store, that's all right 230 00:12:42,852 --> 00:12:46,653 Speaker 3: at the entry, not linked to any of the CCTV or anything. 231 00:12:46,773 --> 00:12:51,052 Speaker 3: So if they don't capture them in the first two cameras, 232 00:12:51,093 --> 00:12:56,053 Speaker 3: often someone that has that hasn't been stopped by security 233 00:12:56,093 --> 00:12:58,413 Speaker 3: for the way they dressed with the hot and the 234 00:12:58,453 --> 00:13:02,053 Speaker 3: mask and the gloves and the shades and everything. They'll 235 00:13:02,093 --> 00:13:04,293 Speaker 3: take the shades off and the mask off the minute 236 00:13:04,333 --> 00:13:05,893 Speaker 3: they get in the store, and they can get picked 237 00:13:05,933 --> 00:13:08,372 Speaker 3: up on the second camera. But it is certainly a 238 00:13:08,533 --> 00:13:11,093 Speaker 3: high alert situation. If you see someone like that, it 239 00:13:11,213 --> 00:13:12,693 Speaker 3: stills trouble with the capital T. 240 00:13:12,973 --> 00:13:15,732 Speaker 2: Gotcha and just on the AURA network, Carolyn. 241 00:13:15,773 --> 00:13:19,173 Speaker 3: Yes, No, it's a completely separate system. You can't transfer 242 00:13:19,252 --> 00:13:22,132 Speaker 3: any data across to any other system. It's not part 243 00:13:22,132 --> 00:13:24,492 Speaker 3: of that. If somebody is ascending in store, you would 244 00:13:24,492 --> 00:13:28,573 Speaker 3: be using your CCTV images to report those through. And 245 00:13:28,612 --> 00:13:32,693 Speaker 3: remembering that not every retailer uses AURA, So whether you'd 246 00:13:32,732 --> 00:13:34,773 Speaker 3: be reporting through the one oh five or one one 247 00:13:34,892 --> 00:13:40,252 Speaker 3: one or through AURA, nothing comes off the facial Refnition 248 00:13:41,012 --> 00:13:43,533 Speaker 3: Technology platform to enable you to do that, you have 249 00:13:43,573 --> 00:13:44,813 Speaker 3: to use your CCTV for that. 250 00:13:45,012 --> 00:13:48,293 Speaker 2: Gotcha, Carolyn, Thank you very much for having to chat 251 00:13:48,293 --> 00:13:51,292 Speaker 2: with us. Very interesting. That is retail in z CEO 252 00:13:51,492 --> 00:13:52,573 Speaker 2: Carolyn Young. 253 00:13:53,333 --> 00:13:56,253 Speaker 1: For more from News Talk SEDB, listen live on air 254 00:13:56,453 --> 00:13:59,173 Speaker 1: or online, and keep our shows with you wherever you 255 00:13:59,213 --> 00:14:01,612 Speaker 1: go with our podcasts on IR Radio.