If you’d written something with a pencil and it became a real object, wouldn’t you think you were either dreaming or inside a movie?
This dream has come true now! A group of brilliant students from China have created an application, which allows you to create a simple sketch, then convert the sketch into a real picture. Isn’t that amazing?
The name of the application is Photosketch. The principle or the idea behind the working of this application is, you draw a rough sketch of something in your mind and label the objects you have placed. For example, if you want an image of birds sitting on the tree, take a pencil and write a rough diagram of tree and the birds sitting on it. Name the objects you have palced like, “Brown Tree” and “Crows”. That’s it. Process it and you will get a real image of the idea you had in your mind.
What this app does?
It searches the web for the words that you had placed like “Brown Tree” and gets the images that suit your position. Then it arranges the images in such a way that it should look real.. Oooh!!
It merges the “Brown Tree” with “Crows” and adds suitable background for the picture. Isn’t that like artificial intelligence?
This is what is the developer’s abstract says about the application:
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.
Here is a video for your clear understanding.