Amazon Rekognition : The rise of Artificial intelligence

reko14

By looking at the word Rekognition you would feel as if it is a wrongly spelled word 🙂 It is nothing but an awesome gift from Amazon to us.

First let us see some background, I attended a training of Artificial intelligence some days back and in that training, we were shown below picture and were told to recognize what it is:

reko9

Within a second everyone said it is an elephant. We can recognize this elephant within seconds because we have years of experience of learning.

Then trainer asked what if a system wants to recognize it within seconds, is it possible? It might be very difficult because if we compare our years of experience with a system’s experience then there is a huge difference, we will have to teach the system to identify what is there in an image.

But the answer of trainer’s question is yes, it is possible with the help of AI. There are millions of images already there on the internet which can be used for Big Data or for AI.

Let us get back to Amazon Rekognition.

It was introduced in re:Invent of Amazon in 2016:

reko1

So basically it takes the image as input and returns data which can be used for different analysis purpose.

So what is Amazon Rekognition?

Amazon Rekognition is a service that makes it easy to add image analysis to your applications.

With Amazon Rekognition you can:

  • Detect objects
  • Detect scenes
  • Detect faces
  • Search and compare faces
  • Identify inappropriate content in images

Amazon Rekognition provides:

reko3

  • Object and Scene Detection
  • Image Moderation
  • Facial Analysis
  • Face Comparison
  • Facial Recognition

Let us see some use cases for different features of Amazon Rekognition:

Facial Recognition:

reko8

Sentiment Analysis:

reko7

Face-Based User Verification:

reko6

Image Moderation:

reko5

Searchable Image Library:

reko4

Interesting isn’t it?

Below are few screenshots of the actual Amazon Rekognition application:

reko10

reko11

reko12

You can see more details about the API and step by step process here if you want to know more.

It may remind you about the God’s eye from the movie The Fast & furious 7\8. That day is near as well with the rise of AI along with AWS 🙂

Happy learning.

Advertisements

New features in Amazon Quicksight

Amazon Quicksight now has some more cool features. Out of those, below are few features which I found very useful.

1) Export to CSV

amazon3

One of the most useful newly added feature is capability of exporting to CSV. This feature was requested by many people and finally Amazon Quicksight is equiped with export to CSV feature

You can now export your data to CSV by selecting the visual you want to export, clicking on the top-right menu icon, and choosing Export to CSV.

2) Possible connectivity with Microsoft Active Directory

amazonBy this feature, you can now connect Quicksight with your on promise AD using Quicksight AD connector. AD connector acts as a proxy which sends the credentials which have been entered for sign in to your on promise AD for validation purpose.

So now users who has their on promise AD credentials, can not log in into Quicksight using existing AD credentials.

Using Managed Microsoft AD, you can easily provision users across multiple cloud and on-premises domains using trust relationships provisioned with the respective ADs.

3) Aggregate filters for SPICE data sets

amazon2

With this feature, you can now put different aggregate filters for SPICE data sets. For example from your data set you want to figure out how many customers has bill amount more than 20k per month.

Apart from this, Quicksight also added some features like KPI charts by which you can present a single aggregated value from a measure, and also comparisons against another measure or over a time period and Custom ranges for Microsoft Excel spreadsheets which automatically detects the cell range of your table in the sheet when you upload an Excel spreadsheet.

To learn more about Quicksight, have a look here.

Insight of Amazon QuickSight

quick5

AWS has launched QuickSight in November 2016 and in very short period of time it became so popular.

First of we will see what is QuickSight?

Amazon QuickSight is a fast, cloud-powered business analytics service that makes it easy to build visualizations, perform ad-hoc analysis, and quickly get business insights from your data. Using our cloud-based service you can easily connect to your data, perform advanced analysis, and create stunning visualizations and rich dashboards that can be accessed from any browser or mobile device.

So in a single line we can say QuickSight is a cloud-powered, business analytics service that lets you quickly and easily visualize your data.

Okay, so you might be wondering what are top most benefits of using AWS QuickSight?

  • It is fast, and faster as well
  • It is easy to use
  • Most importantly it is 1/10th the cost of traditional BI solutions

Interesting right? Now you want to know what would be the best features AWS QuickSight provides?

Here they are:

  • You can choose your data source:

When you log in, Amazon QuickSight seamlessly discovers your data sources in AWS services such as Amazon Redshift, Amazon RDS, Amazon Athena, and Amazon Simple Storage Service (Amazon S3). You can connect to any of the data sources discovered by Amazon QuickSight and get insights from this data in minutes

quick1

  • SPICE – The Super-fast, Parallel, In-memory, Calculation Engine

Amazon QuickSight is built with “SPICE” – a Super-fast, Parallel, In-memory Calculation Engine. SPICE supports rich calculations that help customers derive valuable insights from their analysis without ever having to worry about provisioning or managing infrastructure. Importing your data into SPICE speeds your analytical queries by allowing you to take advantage of its storage and processing capacity. Data in SPICE is persisted until it is explicitly deleted by the user.

  • It is mobile friendly

The iPhone app for Amazon QuickSight lets you access your data anywhere, and explore analyses, stories, and dashboards. Look for Android and tablet support, as well as viewing and creating annotations in offline mode in the future.

quick2

  • It has Smart Visualizations

Amazon QuickSight supports a growing list of visual types including bar charts, heat and tree maps, pivot tables, and others.

It supports:

  • Comparison and distribution
    • Bar charts (several assorted variants)
  • Changes over time
    • Line graphs
    • Area line charts
  • Correlation
    • Scatter plots
    • Heat maps
  • Aggregation
    • Pie graphs
    • Tree maps
  • Tabular
    • Pivot tables

quick3

So finally we will see how it works?

quick4

Now just sign up to Amazon Quicksight and get 1 user and 1GB of SPICE capacity for free. That is the best part here 😉

Happy coding!

Create a free website or blog at WordPress.com.

Up ↑