Nick Johnston

Learn More
We present a system which can recognize the contents of your meal from a single image, and then predict its nutritional contents, such as calories. The simplest version assumes that the user is eating at a restaurant for which we know the menu. In this case, we can collect images offline to train a multi-label classifier. At run time, we apply the(More)
This paper presents a set of full-resolution lossy image compression methods based on neural networks. Each of the architectures we describe can provide variable compression rates during deployment without requiring retraining of the network: each network need only be trained once. All of our architectures consist of a recurrent neural network (RNN)-based(More)
We propose a method for lossy image compression based on recurrent, convolutional neural networks that outperforms BPG (4:2:0), WebP, JPEG2000, and JPEG as measured by MS-SSIM. We introduce three improvements over previous research that lead to this state-of-the-art result. First, we show that training with a pixel-wise loss weighted by SSIM increases(More)
I wanT To monITor my aThleTe buT where do I sTarT? Given the relationships among athlete workloads, injury and performance, athlete monitoring has become critical in the high-performance sporting environment. Sports medicine and science staff have a suite of monitoring tools available to track how much ‘work’ an athlete has performed, the response to that(More)
Picosecond laser ultrasonics is a well established technique for measurement and diagnosis of microand nano-scale structures. One of the major drawbacks preventing widespread acceptance of this technique is that the data acquisitions speeds are slow making imaging applications impractical. We are engaged in a research program to accelerate the data capture(More)
We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas. These methods lead to lower true bitrates for(More)
  • 1