Deep Collector
Automatically build a speaker dataset
How can I build up a dataset for my speaker recognition?
use case: Similarity and reverse search
the challenge
Although training AIs is already very easy, there are so many unknown people in many archives that even uploading three images of the respective person leads to a massive time investment. Thousands of hours of video material thus develop into a data silo whose already contained information cannot be used. Can DeepVA help me to store recurring persons, who currently cannot be named, so that they can be found in the future?
the solution
With the DeepVA Deep Indexer, unlabeled people are referenced as numbers and can then be retroactively labeled in the future. This is comparable to a huge memory card pile, the AI searches for pictures and videos of one person and classifies them as a dataset. In the end, the user only has to assign a name to the respective datasets, and you bring more structure into your archive material.
What results can be obtained?
Assigned but not labeled faces are trained and stored in the database
As soon as the faces are then labeled, all data is then correctly assigned to the face and the name
Unknown faces are referenced using a unique number – this number can be relabeled later
Individuals are labeled across all assets, the footage does not have to be analyzed again
faster data acquisition
COST REDUCTION
faster labelling
Similarity and reverse search
Using Face Index, each person in video and image material can be assigned a number, allowing them to be translated into the metadata afterwards.
Contact us
Enter your email below and we will get back to you as soon as possible.
Related use cases
How can I build up a dataset for my speaker recognition?
How can I recognize less-known or regional people in my footage?
Don’t worry, we reserve our newsletter for important news, so we only send a few updates once in a while.
Designed and engineered in Germany.
Aiconix GmbH
Wannerstraße 19
79106 Freiburg
Germany
The project has indirectly received funding from the European Commission’s Horizon 2020 Framework Programme through the STADIEM project (Grant Agreement 957321)
don't miss the latest news!
Don’t worry, we reserve our newsletter for important news, so we only send a few updates once in a while. No spam!
