#visual recognition

Right now, while you are reading these typewritten words, your hand muscles are moving imperceptibly, but measurably. These movements would be even greater if the words were handwritten.

That’s because your motor system strongly contributes to your perception of language, in part by trying to simulate the movements that were necessary to craft the words you read on a page or screen.

That’s the point of a new paper in the journal Neuroscience Letters by UC Merced graduate student Chelsea Gordon and cognitive science professors Ramesh Balasubramaniam and Michael Spivey.

Their study enhances the campus’s cognitive science focus on embodied cognition, which says the brain guides the body, but the body also guides the brain.

“The conventional thinking was that the brain was modular,” Spivey said. “Each different section was responsible for specific major functions. More and more, though, we are realizing how interconnected the different areas of the brain are.”

“Corticospinal excitability during the processing of handwritten and typed words and non-words” by Chelsea L. Gordon, Michael J. Spivey, and Ramesh Balasubramaniam in Neuroscience Letters. Published online June 9 2017 doi:10.1016/j.neulet.2017.05.021

Facebook is ramping up the training process for visual recognition models #facebook #GPUs #visualrecognition

Deep learning models are extremely important. And they are going to have a pivotal role to play in the world to come. Which is why it is important for large corporations to ensure that they are not lagging behind in the race to train deep learning systems of their own. Along the same, Facebook has announced a major breakthrough in its deep learning capabilities.

In a paper published earlier, the…

By Robert

Hello everyone, sorry about the recent radio silence. Here at BlueChasm, we’ve been working hard on a lot of projects and we’re excited about the next couple of months where we’ll be attending many events. More on that later.

Our previous tutorial uses V2 Beta of visual recognition but they have since moved to V3 which includes amazing services like face and text detection.

Today, I’m going to write a very simple How-To Tutorial on Watson Visual Recognition V3. Lets get started!

Prerequisites: 

First, we need to install the Watson Developer Cloud SDK using pip.

     sudo pip install --upgrade watson-developer-cloud

This python library contains the necessary tools to interact with the Watson services.

You will also need a Visual Recognition API Key. If you don’t have a key, check out this guide to get yours. 

Making the calls:

There are three main API calls to identify Images: Classify, Detect Faces and Recognize Text. Here is a simple way to use them.

NOTE: Watson can take an image file and .zip file as well to get recognized by either of the 3 APIs Just do the following:

Flask Example: 

Here is a flask example that sends an uploaded file to Watson and then prints out the resulting JSON from the call. From here, you can use the data for anything you want.

The file structure is as follows:

HTML File: 

Server File:

By: Alex

If you're developing Node.js applications using IBM Watson Visual Recognition, getting started can be a little bit of a struggle. I'll show you very quickly how to use Node.js, express, and Bluemix to start using Watson.

This can also be adapted for other Watson services if you wish.

First, in Bluemix, go to catalog and under runtimes select "SDK for Node.js". Enter your app name and click create. Follow the start coding instructions for your choice of eclipse, command line, or git.

In the console navigate to the directory of your project. Install the Watson package from npm.

npm install watson-developer-cloud --save

In Bluemix, add a Watson visual recognition service. You can find it in the catalog. Enter a service name and you can bind it now to the app you already created.

We will now add Watson to our app.js. To find your api_key attribute, navigate to your app in the Bluemix dashboard and select "show credentials" under the visual recognition service. Add the following code to your app.js.

var watson = require('watson-developer-cloud'); var visual_recognition = watson.visual_recognition({ api_key: '', version: 'v3', version_date: '2016-05-20' });

If you're reading this farther in the future. Check for the latest version of the Watson module.

Now you can access all of the Watson visual recognition functions. For example, here is how we would run text recognition on a local image file.