-
Task
-
Resolution: Done
-
Neutral
-
None
-
None
-
-
Empty show more show less
-
Empty show more show less
-
Basel 158
-
5
User story:
As a digital marketer, I want to find the right image asset quickly. Image recognition helps me as long as it recognizes objects in typical marketing images and tags the assets accordingly. I expect common marketing subjects ("car", "dog", "person", "office", "beach" etc.) to be always recognized and tagged. I don't expect specialized subjects ("trilobite", "Cockerspaniel", "Daniel Radcliffe") to be always recognized but I am positively surprised if they are.
Internal story:
As a Magnolia Product Manager, I want local image recognition to be sufficiently complete and accurate so that it impresses evaluators. I want typical marketing subjects to be always recognized and tagged. For specialized images I expect the client to use an integrated image recognition service.
Business benefit / value: Reliable and accurate local image recognition makes a great first impression. It convinces evaluators.
Background: Local image recognition is currently limited to ImageNet 1000 synsets (synonym sets). This collection of labels does not represent typical marketing imagery. It is heavily biased towards animals ("African elephant", "hyena", "weasel") while common marketing subjects like "computer", "person" and "shoe" are missing. This means that a neural network pre-trained on Imagenet 1000 classifications does not recognize common marketing subjects.
Acceptance criteria:
- Common marketing image subjects ("man", "woman", "child", "computer", "office", "beach") are recognized 90% of the time.
- At least 3 tags are applied to common marketing subjects. If an easily recognizable image gets no tags it gives a poor first impression.
- Tags are nouns. Exclude verbs, adjectives and adverbs.
Implementation proposal (optional, up to PD to decide):
- For a set of labels that better represent subjects in typical marketing images, use Core Wordnet 5000. It is a list of 5000 core word senses in WordNet. The list contains most frequently used English language words. Download: http://wordnetcode.princeton.edu/standoff-files/core-wordnet.txt
- Use nouns only. Exclude verbs, adjectives and adverbs.
- Generate a new labels JSON file and re-train the neural network on ImageNet images.
Attachments:
- marketing-images.zip – set of common marketing subjects for testing.