Subconscious and Conscious Data: Where AI & Machine Learning Could Create Genuine Value for DAM
Subscription Only
This feature article has been written by Ralph Windsor, DAM News Editor and Project Director of DAM Consultants, Daydream.
Recently I have been working with a client who was dissatisfied with the results they were getting from AI image recognition tools they were using for their DAM initiative.
Subscription Required
You need an active DAM News subscriber account to access this content. If you already have a DAM News subscription, you can log into your account here.
A very interesting read.
We ran a project last year in collaboration with the University of Brighton to test our hypothesis that a custom-built, trainable ML system would give better results than the generic cloud services – even with only a few weeks of development effort. (The result was “yes”).
We came to some similar conclusions as you, in particular that “getting useful results from ML necessitates custom development work”.
It’s only fair for me to point out that we haven’t yet taken this any further e.g. within our DAM solutions.
If you’re interested, see this blog our marketing team wrote about it:
https://www.assetbank.co.uk/blog/the-latest-research-on-artificial-intelligence-and-dam
If you’re _really_ interested, see the paper written by the team at the University of Brighton:
https://cdn2.hubspot.net/hubfs/4056449/image-classification-asset-1.pdf
Glad you liked the article, Martin. Thanks for the two links, I think I’ve read your blog post about this, I’ll check out the University of Brighton paper.
Another incredible deep dive. I loved reading this. Ralph, you are one of this industry’s true treasures. Thank you.
Glad you liked the article, Mark!