Vision
- Classify images based on their content (e.g. photo of a cat)
- Detect and locate objects in a picture using bounding boxes
- Perform image segmentation to identify pixels that belong to objects
- Extract text from scanned documents, pictures, or handwritten notes
- When applied to videos, computer vision is used to detect actions or track movement of objects
What to use it for
- Tag and label objects such as celebrities, locations, and common objects in images and videos to find content faster, enable personalization to customers' behavior and support monetization via contextual advertising
- Review the use of your logo in images and videos to ensure visibility and adequate association of your brand in third party content like influencer posts
- Identify problematic content in images and videos to ensure safety of the content you publish or of the content that is in vicinity of your brand logo
- Classify products according to your specific taxonomy to place products into the appropriate category in your webshop
- Extract handwritten or printed text from scanned forms like invoices, order confirmations, contracts and more to reduce manual processing time and enhance data quality
- Easily train custom models to perform visual inspection on parts to detect anomalies in production processes
- ... and many more ...
