Making Screens Safe for those with Photosensitivity

Technology

This technology uses machine learning methods to detect and modify harmful stimuli in videos. In the forward pass, this technology generates a large dataset of videos. Each video is then corrupted with artifacts, such as flashing lights, which would adversely affect photosensitive individuals. In the inverse pass, the harmful videos created in the forward pass are transformed into innocuous videos without compromising the quality. This inverse pass is accomplished using neural networks that learn to detect and selectively suppress problematic regions. Videos lacking adverse stimuli remain unaffected. The resulting filter may then be generalized to a wide range of new videos.

For individuals with photosensitivity, including photosensitive epilepsy, these filters can be tuned to be more aggressive against specific stimuli. In addition, this technology can be utilized by large content providers or browsers to improve the safety of their video platforms. As the quality of the video is not degraded during the transformation, this method can be applied to a broad range of videos without compromising the visual experience of those without photosensitivity.

Problem Addressed

Photosensitivity is a prevalent condition in which visual stimuli, such as flashing lights, trigger seizures or other adverse reactions. Videos are common sources of these unsafe stimuli, and although there are efforts to reduce certain types of strobing, the range of problematic stimuli is broad, unpredictable, and difficult to filter against. The inventors have developed a method to actively detect and modify harmful stimuli in videos, thereby protecting photosensitive individuals from exposure. Importantly, this method can protect viewers against a wide range of problematic stimuli without degradation of video quality. This invention has broad consumer and business applications to ensure a safe visual environment for all photosensitive individuals.

Advantages

• Method to detect and modify a broad range of harmful stimuli in videos
• Filter can be tunable to individual photosensitivities or broadly applied to video platforms
• Provides safe visual environments without degradation of video quality

Publications

Andrei Barbu, et al. Deep video-to-video transformations for accessibility with an application to photosensitivity. Pattern Recognition Letters. 2020 Sept. doi: 10.1016/j.patrec.2019.01.019.