ChimpFace

Unknown profit model, Open source, Market Shaping Phase, Eager to add new members
Using image analysis techniques (facial recognition) to combat Internet-facilitated wildlife trafficking.

The Problem

Check out our project video for a quick project summary: https://vimeo.com/301107703 --------- The illegal trade of wildlife products is worth billions of US dollars annually. Increasingly, dealers and consumers are turning to Internet social media and e-commerce platforms to illegally sell and purchase (traffic) live exotic animals. Monitoring these platforms for trafficking-related posts can help disrupt the illegal trade in live wild animals, and possibly lead to prosecutions of traffickers. However, monitoring is expensive and difficult to do manually. Live great apes frequently fall victim to Internet-facilitated trafficking. Over 6,000 great apes have been trafficked from the wild since 2005, and a further 30,000 have died in capture-related activities. Researchers have identified hundreds of social media accounts displaying illegally traded great apes, and have manually searched millions of social media photographs for evidence of trafficking. However, this method is cumbersome and prone to error, as many individual great apes are similar in appearance, making them difficult to track through the online trade chain as well as susceptible to misidentification and/or double counting.

Our Proposal

ChimpFace aims to use image analysis techniques (facial recognition) to identify photos on social media and e-commerece websites that are likely linked to trafficking-related activities. Suspicious posts will be flagged as possible trafficking and sent to a team of conservation experts for review. The initial phase of the project will focus on chimpanzees because of their importance to conservation, the frequency at which they appear for sale online, and the availability of large amounts of imagery. We will leverage both publicly available imagery dataset and images we have collected from chimpanzee conservation and research organizations to build a binary chimpanzee image classifier, and then deploy it to monitor social media posts. Depending on the number of posts that are flagged by the image analysis method, we may also add text-analysis to our method to down-select posts based on likely trafficking-related words or phrases (i.e. "chimp for sale").

We Assume that...

There is a role for photographic evidence in criminal proceedings prosecuting wildlife traffickers.

Wildlife traffickers will continue to post pictures of live great apes (and other species) on Internet social media and e-commerce websites.

The global conservation, law enforcement, and technology communities will continue to prioritize and provide funding to combat wildlife trafficking.

Chimpanzees have unique facial features that can be recognized by properly designed facial recognition algorithm.

The wildlife conservation, law enforcement, and technology communities would like to more efficiently detect Internet-faciliated wildlife trafficking.

Internet-faciliated wildlife trafficking will continue to be a problem in the future.

Constraints to Overcome

1. The vastness of the Internet make monitoring for wildlife trafficking-related activities time consuming and tedious (it is like looking for a needle in a haystack. So many webpages to search!). ChimpFace will automate the search process, reducing the amount of man-power hours and financial resources required to effectively police the Internet and identify suspicious posts. 2. Many chimpanzees are similar in appearance. This makes it challenging (if not impossible) to track individual animals through the nine trade chain, as individuals are susceptible to misidentification and/or double counting.

Current Work

1. To create an efficient and reliable tool that can aid in combatting Internet-facilitated wildlife trafficking. 2. To create a tool that is useful and user friendly for conservation organizations, law enforcement, wildlife crime investigators, social media/e-commerece companies, and citizen scientists. 3. To create a tool that we can “scale up” to identify other species involved in Internet-faciliatated trafficking. 4. To collect evidence for wildlife trafficking criminal prosecutions. 5. To end Internet-facilitated wildlife trafficking, and fight other forms of wildlife trafficking.

Current Needs

1. Funding

or
 
DISCUSSIONS & TASKS
IN AREA / PROJECT