machinelearning

AI-Powered App Helps You Colorize Black & White Photos in Seconds

This is amazing. The researchers at UC Berkeley who came up with the automatic colorizer algorithm we first shared back in March, 2016 have released a major update. The software now lets you team up with the algorithm to colorize complex black and white photos accurately in seconds.

A Demo of How Future Cameras May Be Able to Auto-Tag Your Photos

With over a trillion photos created every year now, one feature that could help people make sense of their massive photo collections could be object recognition and automatic tagging. If your camera and photo management software can figure out what's in your shots, it'll make searching through old photos much more easy and intuitive.

Companies and researchers are working hard on pushing this field forward. Photo sharing services are already adding auto-tagging to their systems -- Flickr and Google had to work out some early "racist" bugs -- and now we're getting a glimpse of what the technology could look like live, in cameras.

Study: Flickr Photos Can Predict People’s Movements

Before you head out for your next vacation, you may want to consider what your photos on Flickr reveal about your travel plans. A new study published in the Royal Society Open Science journal used machine learning algorithms to model the mobility of individuals.

By analyzing the embedded timestamp and geographic information within photographs, the researchers were able to accurately predict where a person is most likely currently located and where they may be headed in the future.

Google Researchers Turn 2D Street View Photos Into Smooth 3D Tours

A group of Google researchers have created a new system called DeepStereo that can predict views of scenery it has never seen before. The technology allows a collection of images to be turned into a three-dimensional walkthrough using sophisticated algorithms to fill in areas that were absent from the photographs -- interpolating missing frames for a smooth experience.

The 2-minute video above shows some examples of what the system can create using Street View-style still photos.

Google Apologizes After Photos App Autotags Black People as ‘Gorillas’

Flickr sparked some controversy back in May after it was discovered that the service's new autotagging feature was prone to mislabeling black people as "apes." It looks like Google Photos developers didn't learn from Flickr's embarrassing misstep: a Google developer is apologizing after it was found that Google's Photos app misidentifies photos of black people as "gorillas."

Cameras of the Future Will Be Able to Identify Things They See

One of the emerging trends in the world of photography is the idea of automated recognition and tagging of things found in photographs. Flickr can now suggest autotags for your photos, and Google's new Photos service lets you search through your unlabeled photos using advanced image recognition.

The same technologies are coming for real-time camera features as well. Qualcomm is working on a system called SceneDetect that lets cameras recognize what they're looking at in real time.

Google Working on Seeing Calories in Food Photos

Camera apps these days already have the ability to analyze your scenes before you shoot them, but what if they could analyze your food before you eat it? That's what Google researchers are working on: they're trying to teach a computer to calculate calories from ordinary snapshots of food.