• Unsupervised (requires no labeling):
• Comparing an entire image
• Categorizing an image
• Supervised (requires labeling):
• Finding parts of an image
• Finding and categorizing parts of an image
• Requires little-to-no prepping of data
• Can just give the tool a set of images and
have it produce results
• Extremely easy to get started, results aren’t
always as interesting.
• Need lots of training data
• Needs to be pre-selected/categorized
• Think: Thousands of images.
• If your collection is smaller than this, perhaps
it may not beneﬁt.
• Or you may need crowd sourcing.
• Results can be more interesting:
• “Find all the people in this image”
• imgSeek (Open Source)
• TinEye’s MatchEngine
• Both are completely unsupervised. No
training data is required.