Steve Spencer's Blog

Blogging on Azure Stuff

Face Recognition with Azure ML and Project Oxford

I’ve wanted to use Azure Machine Learning for a while but didn’t know where to start. Microsoft have released some gallery applications for Azure ML to take away some of the complexity and make it easy for developers to use the service. One item in the gallery that will be useful is Project Oxford. Project Oxford offers a number of features and the one I am going to talk about here is the Face API.

With the Face API you can train Azure ML with pictures of a number of people and then use the matching api to see whether any of the trained people appear in the image.

This is easy to setup and there is a good tutorial here: http://www.projectoxford.ai/doc/face/How-To/identifyperson

Firstly you will need to sign up and get a subscription key http://www.projectoxford.ai/doc/general/subscription-key-mgmt

Login to Azure portal with an Azure subscription, The link should open market place. Scroll down to find Face APIs and then click through to the purchase button and purchase. This api is currently free.

Your face api service will now be created. Once complete you need to extract the keys for use in your app. Click on your face api service then click the Manage Button

clip_image001

Click on show to view your key and copy it into your application

clip_image002

Download the face api from https://www.projectoxford.ai/sdk unzip and add to your project, then add a reference in your application.

Follow the code here: http://www.projectoxford.ai/doc/face/How-To/identifyperson

Be aware that when this is run you may get a bad request error (I used fiddler to see the error) when creating a Person Group. This seems to be due to case sensitivity and when I made the parameters lower case it worked! The sample code above is mixed case but the service seems to want all lowercase. Details of the error messages can be found here: https://dev.projectoxford.ai/docs/services/54d85c1d5eefd00dc474a0ef/operations/54f0387249c3f70a50e79b84 The body of the response contains the exact details of the error.

There are limitations on file size so I ended up editing mine down to below 4MB

Once trained you can detect multiple people in one photo graph and will identify those that it knows

I've trained it with a number of people especially as my daughter was identified as her mum :-)

Now I've added her into the training files she is not mistaken.

You might need to play around with the training files especially to take into account hats and glasses.

Enjoy

Pingbacks and trackbacks (1)+

Loading

Steve Spencer's Blog | October 2012

Steve Spencer's Blog

Blogging on Azure Stuff

Windows Azure Queues vs Service Bus Queues

If you have been wondering why you would use Windows Azure Queues that are part of the Storage Service or the queues that are part of the service bus then the following MSDN article will give you full details.

http://msdn.microsoft.com/en-us/library/hh767287(VS.103).aspx

Recent changes in pricing make the choice even harder. There are two specific areas I like that makes the service bus queue a better offering than the storage queues:

  1. Long connection timeout
  2. Topics

The long connection timeout means that I don't have to keep polling the service bus queue for messages. I can make a connection for say 20 minutes and then when a message is added to the queue my application immediately returns the data, which you then process and then reconnect to the queue to get the next message. After 20 minutes without a message the connection closes in the same way it does when a message is received except that the message is null. You then just reconnect again for another 20 minute. The makes your application a more event driven application rather than a polling application and it should be more responsive. You can make multiple connections to the queue this way and load balance in the same way as you would when polling queues.

The following code shows how you can connect with a long poll.

 1: NamespaceManager namespaceManager;
 2: MessagingFactory messagingFactory;
 3: Uri namespaceAddress = ServiceBusEnvironment.CreateServiceUri("sb", "yournamespace", string.Empty);
 4:  
 5: namespaceManager = new NamespaceManager(namespaceAddress, TokenProvider.CreateSharedSecretTokenProvider("yourIssuerName", "yourIssuerKey"));
 6: messagingFactory = MessagingFactory.Create(namespaceAddress, TokenProvider.CreateSharedSecretTokenProvider("yourIssuerName", "yourIssuerKey"));
 7:  
 8: WaitTimeInMinutes = 20;
 9:  
 10: // check to see if the queue exists. If not then create it
 11: if (!namespaceManager.QueueExists(queueName))
 12: {
 13:     namespaceManager.CreateQueue(queueName);
 14: }
 15:  
 16: QueueClient queueClient = messagingFactory.CreateQueueClient(queueName, ReceiveMode.PeekLock);
 17:  
 18: queueClient.BeginReceive(new TimeSpan(0, WaitTimeInMinutes, 0), this.ReceiveCompleted, messageCount);

When a message is received or the 20 minute timeout expires then the ReceiveCompleted delegate is called and a check is made to see if the message is not null before processing it.Once processed another long poll connecting is made and the process repeats. The beauty of this method is that you don’t have to manage timers or separate threads manage the queue.

Topics are private queues that are subscribed to by consumers and each private queue will receive a copy of the messages put into the original queue and are all manages individually. Topics can also apply filters to the message so that they only receive messages that they are interested in.

Further details of Service bus topics and queues

http://www.windowsazure.com/en-us/develop/net/how-to-guides/service-bus-topics/