AWS Machine Learning Blog

Marinus Analytics fights human trafficking using Amazon Rekognition

Marinus Analytics is a woman-owned company, founded in 2014, that builds AI tools that turn big data into actionable intelligence. They are dedicated to using artificial intelligence, such as the facial recognition features available in Amazon Rekognition, to help find human trafficking victims and reunite them with their families.

“We believe that artificial intelligence shouldn’t be feared by humans because it can enable us to accomplish far more good than would otherwise be possible and scale the overall impact,” says Emily Kennedy, President and Co-Founder of Marinus Analytics. “For Marinus Analytics, we have been lucky enough to see lives saved by using AI technology because it has empowered those fighting against human trafficking to accomplish seemingly impossible tasks in the face of what initially seemed like an insurmountable pile of data.”

Marinus Analytics uses artificial intelligence, such as Amazon Rekognition, to provide agencies with tools that assist them in identifying and finding victims, such as Traffic Jam, which assists those working on human trafficking investigations. Rekognition powers Traffic Jam through a facial recognition feature called FaceSearch. With this tool, investigators can now save invaluable time by using image analysis to automatically search through millions of records in seconds. This is a significant improvement compared with methods investigators would have to use without Traffic Jam.

“Without Traffic Jam, investigators are left to manually sift through thousands of online ads,” says Kennedy. “This means they sit at their computer, with a picture of the victim taped to their screen, and compare every photo they see online in the hope that they might find a match. Using AI technology, like Amazon Rekognition, this critical task can now be done with more accuracy and within seconds as compared to days, which is so important in cases where detectives have limited time to find the victim before he or she is moved to the next city.”

When Marinus Analytics was in the development process, they tried multiple computer vision services to see if the technology would complement the tools they provide to those investigating human trafficking cases. They tested their data against many services, but it unfortunately didn’t prove to be useful since the images they needed to analyze were usually grainy, with faces far away from the camera, and the pictures were often taken in bad lighting.

However, they discovered Amazon Rekognition in 2017 and realized that it was the type of AI tool they needed.

“As we tested our data with Amazon Rekognition, the results were astounding. This was the type of AI technology that we had been hoping to integrate into our suite of tools,” says Cara Jones, CEO and Co-Founder of Marinus Analytics. “As soon as we incorporated Rekognition into the Traffic Jam suite through FaceSearch, we almost immediately started hearing success stories. It has been a critical factor in helping Marinus Analytics find victims and reunite them with their families.”

Another way Marinus Analytics uses Amazon Rekognition to aid in the fight against human trafficking is by using the DetectText API. This function can detect text in images, extract them, and convert them into machine-readable text. Since millions of human trafficking ads on the internet have overlaying text on the image, this feature can extract all of that text, which can then be collated and organized so investigators can more easily search through it.

Although the fight against human trafficking can seem daunting, Marinus Analytics has already seen success stories. For example, in northern California investigators were able to use this technology to find a missing 16-year-old who was being sold online for sex.

“By uploading a photo of the victim submitted by the family and using Traffic Jam FaceSearch, the detective was able to find a match that had a high confidence score in seconds,” says Kennedy. “After he looked at the location and timing, he deduced that this had to be the missing person he had been looking for. Within just a few days the victim was reunited with her family.”

In another recent case, a detective was looking for a number of victims, one of whom had been missing for two years. Since any photo used in the investigation would be at least two years old, the detective had little confidence it would result in fruitful leads. However, using FaceSearch, the detective was able to use the two-year-old photo to find a match of the victim and build a successful case against her trafficker.

This same case had another victim that had been missing for over a year. As the detective was continuing his search, he felt he had hit a dead end. However, after reviewing the FaceSearch results, he discovered that one of the top matches had a phone number that was registered to the victim’s real name. He hadn’t recognized her initially because of her changed appearance, however Traffic Jam FaceSearch was still able to make a successful match. The detective ended up identifying 20 victims of an extremely violent trafficker. With the assistance of AI, this detective was able to create a case against this trafficker in three months, much faster than the two years it would usually take, and ensure that the trafficker was put in prison.

“This technology is extremely powerful, so it is imperative that we use it for positive ends that change the world for the better,” says Kennedy. “With technology, such as Amazon Rekognition, we can effectively fight crimes like human trafficking, scale our impact, and accomplish something invaluable—reuniting those who are exploited with their families, and giving them a chance to live a free and full life.”


About the Author

Kaiser Larsen is a Product Marketing Manager for AWS artificial intelligence solutions. Outside of work you’ll find him hiking, cooking for family and friends, and eating ice cream whenever there’s an excuse to celebrate.