use case: improving visual search
How can I efficiently find what I’m really looking for in my footage?
The challenge
Unlabeled data
The increasing amount of visual data poses a major challenge for many companies, especially when it comes to retrieving specific people or places in images or videos. Among countless data, the search usually turns out to be like the famous needle in a haystack. This not only means high costs but also many hours of redundant work like manually tagging files, maintaining consistent keywording and an exhausting categorization process.
So, how can DeepVA help you find the people or places you’re looking for faster and more efficient?
the solution
Deep Media Analyzer
DeepVA’s AI solution for image and video recognition enables the automatic assignment of relevant tags or keywords to extensive image and video collections. The AI models have been trained with more than 3,000 objects, over 21,000 personalities, as well as more than 30,000 landmarks and 300,000 logo variations from day-to-day life. It can additionally be individualized with custom tags to achieve the highest accuracy. This not only reduces redundant and complex processes, but provides an automated environment for all the searches of the users.
What results can be obtained?
Extensive extraction of a wide range of metadata, with frame accuracy
Low staff effort compared to manual keywording
Existing archives benefit from significantly improved searchability and new discoveries in their collection
faster data acquisition
COST REDUCTION
faster labelling
Improving visual search
Function overview
Face recognition
Detects and identifies the faces of public figures in a variety of categories such as politics, sports, business and entertainment.
Landmark recognition
Identifies all important sights, architectural structures and natural monuments across Europe.
Visual concepts
Detects and labels various objects and scenes, from general to more specific ones.
QR-Code Detection
Using QR codes, important information and links can be integrated directly in the footage, our QR code detection then makes them readable again.
Logo recognition
Using QR codes, important information and links can be integrated directly in the footage, our QR code detection then makes them readable again.
Text recognition
Often important information is already contained in the image, our text recognition recognizes it and makes it usable.
Contact us
Do you have any questions?
Related use cases
Take a look at our other use cases
Improving video recommendations
How do I create better suggestions based on viewing behavior without a comprehensive user profile?
Speeding up research time
How can I recognize people and objects more quickly and establish references between them?
Equality and diversity insights
How can I get quick insights into my content’s diversity and equaltiy status?
