>>> [!note] Migrated issue <!-- Drupal.org comment --> <!-- Migrated from issue #3545343. --> Reported by: [tonypaulbarker](https://www.drupal.org/user/807484) >>> <h3 id="summary-problem-motivation">Problem/Motivation</h3> <p>We can potentially capture and use extended data about media items, including: subjects and objects of the image; location information; contextual information from content usage; metrics on mood such as happiness and sadness; dominant colour information; lighting information.</p> <p>Perhaps JavaScript tools like those used in Editoria11y module and OpenCV.js face-api.js can be a useful part of the AI mix, save resources by performing some work without using AI services and integrate with AI services. </p> <p>How to then store and retrieve the data captured by these tools is not in scope of this particular issue. Perhaps the data <a href="https://www.drupal.org/project/ai_initiative/issues/3545342">can be stored in a vector database</a>. </p> <h3 id="summary-proposed-resolution">Proposed resolution</h3> <p>Investigate available tools and their relative merits. Investigate whether different tools can integrate with different AI service providers<br> (examples Azure computer vision <a href="https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/">https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/</a> <a href="https://learn.microsoft.com/en-us/rest/api/computer-vision/">https://learn.microsoft.com/en-us/rest/api/computer-vision/</a><br> and Google Cloud Vision <a href="https://cloud.google.com/vision/docs">https://cloud.google.com/vision/docs</a> )</p> <h3 id="summary-remaining-tasks">Remaining tasks</h3> <p>- Investigate and explore capabilities of JS libraries and tools<br> - Investigate and explore capabilities of AI provider tools<br> - Document general findings<br> - Provide code examples and technical information that can be used to help realise stories in the AI media track.</p> > Related issue: [Issue #3541825](https://www.drupal.org/node/3541825)