Face Recognition Model using Azure Custom Vision Service

Let us start training the model and then we would do a quick prediction test on azure itself and then would finally, create the python code for performing the designated tasks.

Step 1

Capture photos of the team members. These photos will be provided to the model for training. The model is based on Supervised Learning, as while uploading the images we provide labels to them.

Now, comes the part where we need to create the model with the dataset. We are creating the model over the azure platform.
Azure provides services which provide you with the pre-trained model as well as one in which you can create your own as well.
Computer Vision in Azure is a serviec that lets you play around with the pre-created models whereas Custom Vision is the one which lets you create your own.

Select the option Both because we are going to use the model for training as well as prediction.
Select appropriate Subscription and Resource Group.
Select the same Location & Pricing Tier for both the resources being created.

Click on “Go to resource”.
Then click on Custom Vision Portal.

Sign in into the portal, with the same Microsoft account, as the cloud portal.

Click on create a New Project.

Provide a name and description. Select the resource from the drop down (you created already).
Project Type: Classification
MultiClass Classification.
Domains: If your business logic is in the options supported by Azure then select that, else go for a general model.

Click on Create.

Now it asks you to add image, so 1 by 1 add images of the team members.

Provide the correct label (here in my case is the name of the person) and click on Upload.
Click Done after image upload.

Then choose your desired training type and click on Train.

Check the accuracy of your model, by clicking on Quick Test and provide the testing images.

Vikash — 65.8%
Khushi — 62.8%
Daksh — 96.3%
Madhhav — 91.7%

Publish the model once you are satisfied with the results.

You need to remember the model name here. It will be used once you are going to use this model in your python code. We also need some more details about the model such as project ID, Endpoint, and the key.

Click on the Gear icon ⚙ on the same page.
These are the details of the model.

Now click on the eye icon 👁 on the top left corner and now click the Gear icon ⚙ on this page. This will give the details of the predictor. From here we need the KEY.

Our model is ready, now we need to use this model and perform the designated tasks:
1. Send mail
2. Send Whatsapp Messages
3. Create AWS Instance, EBS Storage and attach it to the instance
4. Open LinkedIn profile

Daksh- send whatsapp message
Khushi- AWS Instance
Madhhav — Send Mail
Vikash — Open LinkedIn

For any queries, corrections, or suggestions you can always connect with me on my LinkedIn.




Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

NGBoost algorithm: solving probabilistic prediction problems

SVD in Machine Learning: Underdetermined Least Squares

Autoencoders in TensorFlow — part 1

Image aesthetics quantification with a convolutional neural network (CNN)

Model Pruning in TensorFlow

Influenza Estimator — Random Forest Regression

Mixup way of Data Augmentation

Learning ML — Log[0]

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
khushi thareja

khushi thareja

More from Medium

To add GitHub configuration to your FlutterFlow project and pull code from Git to Android Studio.

Encrypting Secret Data Stored in ETCD Database.

Setting Up Redis And Celery To Work With Django On Windows (Asynchronous Execution)

Class and instance attributes