An Algorithm For Perfect Pictures

Image result for An Algorithm For Perfect PicturesCreating a perfect digital picture has just become easier – researchers at the Carnegie Mellon University have developed an algorithm that can remove unwanted objects/bits of photos and replace it with something that fits perfectly.

The new algorithm works like this: first, it scans online photo libraries (Photobucket, Flickr, etc) in order to discover camera position, light sources, composition and so on in a photo. Then, it uses this data to search for objects (landscapes, cars, walls, trees, etc) that match the original photo. In the end, the algorithm replaces the thing you originally didn’t like about your pic and replaces it with something that fits.

Clearly, in order to create pristine pics, this algorithm has to go through a lot of work. For example, the first thing it does is performing a broad analysis of the images in the database so it can eliminate those that are not appropriate or don’t fit the pic. But, it retains closest 200 for further analysis. The next phase consists of cropping the best 20 images and adding that material to the original image in order to find the best fit.

The result? A perfect digital pic.


Digital Trends (


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s