Posts Tagged ‘algorithm’

Adobe Shows Off Features for Changing Time of Day Lighting and Removing Fog

timeofday

At the Adobe MAX 2014 conference this past week, Adobe showed off some of the crazy technology current brewing in the company’s labs. Two of them offer a glimpse at what may soon be available to photographers in Photoshop: changing the time of day (i.e. lighting) in photographs with a simple slider and removing haze from a scene automatically.
Read more…

This Algorithm Changes the Time of Day, Season and Weather in Your Photos

WeatherChangingBrownUni

Researchers at Brown University have created an intriguing little algorithm that allows you to alter the weather, time of day and even season in your outdoor photographs.

Read more…

MIT Algorithm Tries to Predict How Many Likes Your Photo Will Get Per Day

MIT_3

A photographer’s primary concern when taking a photo might not be “I wonder how many likes this will get,” but being able to gauge popularity could still come in handy when you’re trying to decide which photos to upload to your favorite sharing site.

Enter MIT PhD candidate Aditya Khosla and his new algorithm that does just that: tells you how popular your photos will be before you even upload them. Read more…

These Photos Contain Exactly One Pixel of Each of the 16 Million RGB Colors

rgb4

For you and me, RGB color spaces may just be an obscure but important mechanism towards achieving properly color-balanced photos. For a certain group of image nerds, however, it’s the whole enchilada. Read more…

New Algorithm Can Pick Out Photo Fakes by Looking at Shadows

shadow

As post-production software continues to become more and more powerful, researchers are doing their best to keep up by developing new methods of spotting digital photo fakes. In the past, we’ve seen that noise patterns and even Twitter trends can help spot fakes, but a new method out of UC Berkeley is taking a look at something else entirely: the shadows. Read more…

Photo Series Uses Face Detection to Spot Faces in Clouds

Cloud Face 1

As humans, it’s only natural to take a look at the sky and perceive to see an object, a face, an animal. Computers, too, are capable of this perception. However, they may be capable of finding things that the human eye can’t, or just might not notice.

In a project called “Cloud Face“, Seoul, South Korea-based Shin Seung Back and Kim Yong Hun of aptly-named ‘Shinseungback Kimyonghun‘ have pointed cameras up at the sky and let complex algorithms detect faces in the passing clouds.
Read more…

Clipping Magic Helps You Easily Remove Picture Backgrounds

Clipping Magic Dog

Here’s a tool you may not have heard about but may useful at some time in the future. It’s called Clipping Magic, and it’s designed to remove backgrounds from user-uploaded pictures.

The concept is rather simple, you upload an image, mark the areas in the background you don’t want in red, and mark the areas in the foreground you do want in green. The website’s algorithm takes over and (hopefully) produces a background-free picture. Sounds simple, doesn’t it? But how does it fare when used for an image with a background you actually want to remove?
Read more…

UT Austin Launches Free Enlarging and Denoising Web App

rcmwebapp2

Movies and TV shows have a knack for making it seem as if you could take a horrible, low-resolution image and turn it into a high-res masterpiece — the term “enhance” has become almost comical. And for every mention of magical television enhancement, there’s mention of some special algorithm at work that makes it happen.

Well, the University of Texas at Austin’s RCM Tools web app isn’t quite up to cable drama standards, but it’s their attempt to apply special algorithms to image enhancement and denoising, and it’s free for photographers to experiment with. Read more…

Thermal Cameras Could One Day Have Drunk-Face Recognition

Over the past decade, many airports around the world have adopted special thermal cameras that can determine whether or not a passenger has a fever. The goal of these cameras is to prevent infectious diseases from spreading and causing an epidemic (or pandemic). Greek scientists Georgia Koukiou and Vassilis Anastassopoulos recently came up with a similar concept, except their thermal camera is used to detect drunk people instead of contagious people.
Read more…

EverPix Building Semantic Photo Search for Giant Picture Libraries

As people snap more and more digital photos, being able to organize those photos into useful sets is becoming increasingly important. Facial recognition algorithms are quickly becoming a standard feature in popular photo origination programs (e.g. iPhoto), but people-sorting is only the tip of the “semantic photo search” iceberg. Cloud photo service EverPix is one company that’s currently working to take photo recognition beyond faces. Sarah Perez of TechCrunch writes,

[...] the eventual goal for Everpix is to become the default way people choose to view and share photos. One development which could help it get there is the image analysis technology the company has been developing in-house. As people’s photo collections grow exponentially over the years, it’s something that will become more valuable in time. Using generalized semantic tagging techniques, Everpix is building algorithms that can identify what the photo is of – meaning, whether it’s a person, a night or day shot, a wide or close shot, a city scene, a nature photo, a photo of a baby, or a vehicle, or a photo of food, among many other things.

What’s important here is that the way they’ve built this to scale. After training the system on a minimal amount of photos, Everpix can then look for other photos in a user’s collection that match that signature without reprocessing the entire photo collection.

In the future, we’ll likely be able to search for photos with photos. Looking for a particular photo that you took at a popular tourist landmark? Just show the app a similar photo found online, and voilà, yours appears.

Cloud Photos Service Everpix Exits Beta With New Website & iPad App; Semantic Photo Search Coming Soon [TechCrunch]