Ferretly performs image content analysis to identify specific risks such as explicit/racy, drugs and alcohol and violent images. In addition, Ferretly will extract text from the images such as in the case of memes, and analyze the text in the same way all text on the posts are analyzed. If an image contains someone holding a sign, Ferretly will attempt to extract the text from the sign as well. Ferretly will analyze text within images across the 10 text based risk classifications as well as keyword matches.
Keywords can also be used to identify specific content which may appear in the images. In this way you can extend the capability of the default image-based risk classifications to virtually unlimited use/cases. For example, if you were investigating a workers compensation fraud case whereby the subject claims they were rendered incapacitated from an accident, you may want to know if they were running/jogging or working out from an image they posted online. In this case, you could enter a keyword such as running and/or gym and Ferretly would flag any post with images containing this content. Ferretly can identify general objects, locations, activities, animal species, products, and more.
Below is a sample image containing labels and text which would allow you to flag the image within Ferretly using custom keywords. Ferretly supports over 10,000 custom labels for image content analysis. Keep in mind, labels are supported in English only.
Labels include: Bicycle, Tire, Wheel, Tower
Text includes: Electric, Uber, Jump
In this case, you could any of the above keywords to your settings profile, and Ferretly would flag the post containing this image.
Image resolution will dictate the effectiveness of the image content analysis. In general, the higher resolution the better.