The human brain’s ability to recognize objects is remarkable. If you see  under unusual lighting or from unexpected directions, there’s a good chance that your brain will still recognize it, and it’s considered an anamoly when it doesn’t. This robust and precise object recognition is a holy grail for artificial intelligence developers. How our brains do this, however, is still a mystery.  Here’s an interesting article from MIT on how researchers may be on to something powerful in the computer vision space.

Think of feedforward DCNNs, and the portion of the visual system that first attempts to capture objects, as a subway line that runs forward through a series of stations. The extra, recurrent brain networks are instead like the streets above, interconnected and not unidirectional. Because it only takes about 200 ms for the brain to recognize an object quite accurately, it was unclear if these recurrent interconnections in the brain had any role at all in core object recognition.

Perhaps those recurrent connections are only in place to keep the visual system in tune over long periods of time. For example, the return gutters of the streets help slowly clear it of water and trash, but are not strictly needed to quickly move people from one end of town to the other. DiCarlo, along with lead author and CBMM postdoc Kohitij Kar, set out to test whether a subtle role of recurrent operations in rapid visual object recognition was being overlooked.

Computer vision is real and has quickly gone from cutting edge and into the mainstream.  Here’s a great article on getting started with computer vision that’s worth checking out.

In 2012, AlexNet took first place at the ImageNet Large Scale Visual Recognition Challenge, marking the first time a convolutional neural network had won the image classification competition. One more factor that made this achievement much more significant is that AlexNet showed twice the accuracy than the second-place participant. […]

Here’s an interesting article in Forbes on how computer vision is being applied in the real world.

Even though early experiments in computer vision started in the 1950s and it was first put to use commercially to distinguish between typed and handwritten text by the 1970s, today the applications for computer vision have grown exponentially. By 2022, the computer vision and hardware market is expected to […]

I’m glad to see that the Azure Custom Vision Service is getting some press. It’s an easy and simple way to build your own computer vision models without having to train on thousands (or tens of thousands) of images. In fact, as little as 15 images can yield workable results.

Here’s an article in www.itbusiness.ca about the service.

“Customers can train their own custom image classifiers and object detectors,” said Tina Coll, the product marketing manager at Microsoft Corp. “For example, a company could choose to detect their own logo in the video of a sports event to track the impact of their advertising or a student might want to count the number of animals passing in front of a nature camera.”

AI is set to disrupt every field and every industry. Healthcare, in particular, seems primed for disruption. Here’s an interesting project out of Stanford.

“One of the really exciting things about computer vision is that it’s this powerful measuring tool,” said Yeung, who will be joining the faculty of Stanford’s department of biomedical data science this summer. “It can watch what’s happening in the hospital setting continuously, 24/7, and it never gets tired.”

Current methods for documenting patient movement are burdensome and ripe for human error, so this team is devising a new way that relies on computer vision technology similar to that in self-driving cars. Sensors in a hospital room capture patient motions as silhouette-like moving images, and a trained algorithm identifies the activity — whether a patient is being moved into or out of bed, for example, or into or out of a chair.

Here’s an interesting article on “oscillatory neural networks” and how physicists trained it to perform image recognition.

An oscillatory neural network is a complex interlacing of interacting elements (oscillators) that are able to receive and transmit oscillations of a certain frequency. Receiving signals of various frequencies from preceding elements, the artificial neuron oscillator can synchronize its rhythm with these fluctuations. As a result, […]