If you read our last blog post about the early days of clipart, you might understand that we’re heavily driven by a desire for good user experience and simplicity. Two developments in the clipart industry are big motivators for why we’re doing what we’re doing:
The first reason is that clipart has gone from a quality game to a quantity game. In the past few years, we’ve seen numerous sites pop up that offer just a tiny sliver of low-quality clipart. This results is a poor user experience for everyone: you’re forced to conduct numerous searches until you find exactly the image you’re looking for. Finding related images is really hard -- but does it have to be that way?
This is where we’re applying machine learning technology - the same kind of algorithms that drive your Facebook or Twitter feed to surface what it thinks are the most relevant stories from thousands of possible options - to the world of clipart. Our team of human curators is finding the best clipart, properly identifying the source and author, and then tagging it in a way that facilities discovery and recommendation by our engine.
The second reason for our site is because the biggest sources of clipart no longer exist. It used to be not too long ago that you could open up your Microsoft Word or Powerpoint and easily have access to thousands of curated images on hand, ready to go. Did you know if you try to do the same in Office 365, Microsoft simply redirects you to Bing’s image search? What a travesty: a formerly good user experience is now poor.
Human curation and having an eye for the “good” clipart - if there is such a way to define images - is what we’re bringing to the table here. When you execute a search for “cat clipart”, we believe you should only see relevant, usable pieces of cat clipart. And if we detect that many people are passing up one piece of cat clipart for another, our technology will prioritize and adjust the importance of each piece until only the most applicable images show at the top. But all this is only possible because we have a team of dedicated clipart geeks doing the research for what we’re calling our “Clipart Genome.”
Hopefully this gave you a peek into what we’re doing here. Vakanzi is a young site and we’re building out lots of cool tech and features. Stay tuned, and as usual - email us at email@example.com if you have questions or feedback!