With over a trillion photos created every year, 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 easier 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.
A company called TeraDeep is working on a product called the Learning Camera. By augmenting a digital camera with deep learning, the company gives the camera the ability to recognize people, pets, faces, and all kinds of objects that are found in scenes. In addition to using pre-trained detectors, the camera can be trained to recognize new objects as well.
Here’s a 2-minute demonstration of a TeraDeep camera being taken around a house. The words in the upper-left-hand corner show what the camera is detecting in the shot in real-time:
The camera above was taught to recognize 1,000 different things using a training set of 10 million photos.
It’s the “first truly smart camera,” TeraDeep says. If you’d like to try out the technology for yourself, you can find the code for a demo app over on GitHub.
Qualcomm, with the upcoming release of its Snapdragon 820 mobile phone processor, intends to add a similar functionality. Called SceneDetect and derived from their research at the cognitive technology Zeroth Project, it intends to be the first commercial application of this technology.
Similar to TeraDeep, SceneDetect can recognize thousands of object on the fly. One of its advantages is that it doesn’t need to be connected to the cloud, making auto tagging effective even out of range. Samsung, LG, HTC, and Sony are some of the companies planning to soon release phones powered by the Qualcomm Snapdragon 820.
Author: Michael Zhang
Michael is a photography enthusiast, entrepreneur, and programmer based in Davis, California, an hour east of San Francisco. He is the founder of Petapixel, Photoblog and Bokeh, and graduated from the University of California, Berkeley with two degrees in computer science.