Use a pretrained image classifier to power a reverse image search engine like the Tineye or GoogleImage search. Returns only from a rather select set of images.
Try it out below:
A set of images representing the categories in wikidata is indexed using Google's Inception model. For each image we extract the top layer's vector. The uploaded image is treated the same - displayed are the images that are closest.
For more information, see the blog post, or check out the code on Github