Extracting text from images is not easy (who would have guessed?)
At its core, Lighthouse is an idea we have been discussing in Connected Devices: can we build a device that will help people with partial or total vision disabilities? From there, we started a number of experiments. I figured out it was time to braindump some of them. Our problem Consider the following example: How do we get from this beautiful picture of Mozilla’s Paris office to the text “PRIDE and PREJUDICE”, “Jane Austen”, “Great Books”, “Great Prices”, “$9.