Photosketch is a new cool imaging buzzword. Imagine a tool that will let you sketch images, tag them with textdescription, sketch some other image and tag it and input to the system add some background description and what you get: a high quality image fascinatingly similar to the one you have just sketched. To describe it more here is a video:

PhotoSketch: Internet Image Montage from tao chen on Vimeo.

Their abstact:

We present a system that composes a realistic picture from a simple freehand sketch annotated with text labels. The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet. Although online image search generates many inappropriate results, our system is able to automatically select suitable photographs to generate a high quality composition, using a filtering scheme to exclude undesirable images. We also provide a novel image blending algorithm to allow seamless image composition. Each blending result is given a numeric score, allowing us to find an optimal combination of discovered images. Experimental results show the method is very successful; we also evaluate our system using the results from two user studies.

Some bloggers are tagging this as the next Photoshop. Sorry but I have to disagree. I once read in Seth Godin’s blog:

Don’t try to be the ‘next’. Instead, try to be the other, the changer, the new

I am not a photo or imaging expert. But this Photosketch is a new concept for me and I hope that Photosketch will be some sort of a changer, the One that may innovate the imaging game.