A large cable operator wanted to enrich content provider metadata with enhanced information and images. After an initial concept alfa1 developed a complete solution based on a dynamic and constantly evolving algorithm.
VTR- Metadata enhancement with AWS Rekognition
alfa1 developed an initial concept followed by a complete solution for an operator that wanted to enrich content provider metadata with enhanced information and images. The algorithm is dynamic and constantly being evolved. A validation step in the workflow allows manual checks required by the operator to be enforced.
Amazon Rekognition makes it easy to add image and video analysis to your applications using proven, highly scalable, deep learning technology that requires no machine learning expertise to use. With Amazon Rekognition, you can identify objects, people, text, scenes, and activities in images and videos, as well as detect any inappropriate content.
- Serverless solution, scalable and cost effective (pay when you use)
- Machine learning on the metadata suggestion algorithm
- User validation loop