Amazon’s efforts through Amazon Web Services Inc. have been largely focused on simplifying cloud compute, but the company’s tendency toward innovation has resulted in greater accessibility to machine learning through services like the image recognition solution AWS Rekognition.

Leveling the artificial intelligence playing field has created opportunities for companies not traditionally rooted in tech to benefit from its developments and improve processes across industries. Chris Adzima (pictured), senior information systems analyst at the Washington County Sheriff’s Office, uses Rekognition to reduce the painstaking manual labor previously necessary to identifying persons of interest in surveillance footage.

“I indexed about 300,000 booking photos … and put that into a recognition collection. Now I can use the simple tools that AWS gives me to search against that index for any new image that we get in … allowing us to get identification within seconds,” Adzima said.

Adzima spoke with John Furrier (@furrier), co-host of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, and guest host Justin Warren (@jpwarren), chief analyst at PivotNine Pty Ltd., during the AWS re:Invent event this week in Las Vegas, Nevada. They discussed Adzima’s process in adopting Rekognition and which AWS tools he’s interested in integrating with the Washington County Sheriff’s Office next. (* Disclosure below.)

Streamlining safety

Before adopting Rekognition, the process of identifying people based on photos was manual, requiring the Sheriff’s Office employees to review a catalog of photos by hand. This lack of efficiency wasn’t only tedious and not cost-effective, it lengthened the time that a crime went unsolved. Rekognition greatly improved this process, according to Adzima.

“With booking photos, I can identify people with a very high level of certainty if they’ve been in our jail. … When you have the data, it’s very simple” Adzima said.

Simplicity characterizes Adzima’s experience with Rekognition from the beginning, with implementation of the solution taking only three days. “It was extremely easy. … I had the photos uploaded and the ability to actually run the searches via the API … in a workable prototype of product,” he said.

As a result of the service’s success, Adzima is looking into new AWS solutions to further improve processes at the Sheriff’s Office, as well as increase the overall safety of the community. Amazon Rekognition Video has the potential to enable better facial identification in grainy surveillance footage, and the newly developed AWS DeepLens can create consistency across the categorizations for scars, marks and tattoos that the department uses to identify potential suspects.

“Opening this stuff up to us allows us to build these things like facial recognition and other things based on machine learning and ultimately keep our citizens safe through the work that AWS does in getting this to us,” Adzima said.

While AWS solutions have been proven to improve work at the Sheriff’s Office, Adzima is adamant they will never replace human employees. “We give them [tools] so they don’t have to do the things like flipping through that book for hours. … They can be out in the field following the leads, keeping the community safe, and apprehending these criminals,” he said.

For the price, Adzima is confident AWS will remain integral to processes for the foreseeable future. “I spend $6 per month for my AWS bill. That’s extremely easy to sell to taxpayers. … Even if we solve one crime, we’ve already seen a return on our investment,” he concluded.

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of AWS re:Invent. (* Disclosure: Amazon Web Services Inc. sponsored this segment of theCUBE. Neither AWS nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE