Windows 10: Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different...

Mustafah Hussien 3 · Jun 10, 2022

Face verification Azure service

:)

Brink · Jun 10, 2022

Cognitive Services APIs: Vision

What exactly are Cognitive Services and what are they for? Cognitive Services are a set of machine learning algorithms that Microsoft has developed to solve problems in the field of Artificial Intelligence (AI). The goal of Cognitive Services is to democratize AI by packaging it into discrete components that are easy for developers to use in their own apps. Web and Universal Windows Platform developers can consume these algorithms through standard REST calls over the Internet to the Cognitive Services APIs.

The Cognitive Services APIs are grouped into five categories…

Vision—analyze images and videos for content and other useful information.

Speech—tools to improve speech recognition and identify the speaker.

Language—understanding sentences and intent rather than just words.

Knowledge—tracks down research from scientific journals for you.

Search—applies machine learning to web searches.

So why is it worthwhile to provide easy access to AI? Anyone watching tech trends realizes we are in the middle of a period of huge AI breakthroughs right now with computers beating chess champions, go masters and Turing tests. All the major technology companies are in an arms race to hire the top AI researchers.

Along with high profile AI problems that researchers know about, like how to beat the Turing test and how to model computer neural-networks on human brains, are discrete problems that developers are concerned about, like tagging our family photos and finding an even lazier way to order our favorite pizza on a smartphone. The Cognitive Services APIs are a bridge allowing web and UWP developers to use the resources of major AI research to solve developer problems. Let’s get started by looking at the Vision APIs.

Cognitive Services Vision APIs

The Vision APIs are broken out into five groups of tasks…

Computer Vision—Distill actionable information from images.

Content Moderator—Automatically moderate text, images and videos for profanity and inappropriate content.

Emotion—Analyze faces to detect a range of moods.

Face—identify faces and similarities between faces.

Video—Analyze, edit and process videos within your app.

Because the Computer Vision API on its own is a huge topic, this post will mainly deal with just its capabilities as an entry way to the others. The description of how to use it, however, will provide you good sense of how to work with the other Vision APIs.

Note: Many of the Cognitive Services APIs are currently in preview and are undergoing improvement and change based on user feedback.

One of the biggest things that the Computer Vision API does is tag and categorize an image based on what it can identify inside that image. This is closely related to a computer vision problem known as object recognition. In its current state, the API recognizes about 2000 distinct objects and groups them into 87 classifications.

Using the Computer Vision API is pretty easy. There are even samples available for using it on a variety of development platforms including NodeJS, the Android SDK and the Swift SDK. Let’s do a walkthrough of building a UWP app with C#, though, since that’s the focus of this blog.

The first thing you need to do is register at the Cognitive Services site and request a key for the Computer Vision Preview (by clicking on one of the “Get Started for Free” buttons.

Next, create a new UWP project in Visual Studio and add the ProjectOxford.Vision NuGet package by opening Tools | NuGet Package Manager | Manage Packages for Solution and selecting it. (Project Oxford was an earlier name for the Cognitive Services APIs.)

For a simple user interface, you just need an Image control to preview the image, a Button to send the image to the Computer Vision REST Services and a TextBlock to hold the results. The workflow for this app is to select an image -> display the image -> send the image to the cloud -> display the results of the Computer Vision analysis...
Click to expand...

Read more: https://blogs.windows.com/buildingap...s-apis-vision/

Brink · Jun 10, 2022

Microsoft improves facial recognition ability to recognize gender

Microsoft announced Tuesday that it has updated its facial recognition technology with significant improvements in the system’s ability to recognize gender across skin tones.

That improvement addresses recent concerns that commercially available facial recognition technologies more accurately recognized gender of people with lighter skin tones than darker skin tones, and that they performed best on males with lighter skin and worst on females with darker skin.

With the new improvements, Microsoft said it was able to reduce the error rates for men and women with darker skin by up to 20 times. For all women, the company said the error rates were reduced by nine times. Overall, the company said that, with these improvements, they were able to significantly reduce accuracy differences across the demographics.

The higher error rates on females with darker skin highlights an industrywide challenge: Artificial intelligence technologies are only as good as the data used to train them. If a facial recognition system is to perform well across all people, the training dataset needs to represent a diversity of skin tones as well as factors such as hairstyle, jewelry and eyewear.

The team responsible for the development of facial recognition technology at Microsoft, which is available to customers as the Face API via Azure Cognitive Services, worked with experts on bias and fairness across Microsoft to improve a system called the gender classifier, focusing specifically on getting better results for all skin tones.

The Face API team made three major changes. They expanded and revised training and benchmark datasets, launched new data collection efforts to further improve the training data by focusing specifically on skin tone, gender and age, and improved the classifier to produce higher precision results.

“We had conversations about different ways to detect bias and operationalize fairness. We talked about data collection efforts to diversify the training data. We talked about different strategies to internally test our systems before we deploy them,” said Hanna Wallach, a senior researcher in Microsoft’s New York research lab and an expert on fairness, accountability and transparency in AI systems.

Wallach and her colleagues provided “a more nuanced understanding of bias,” said Cornelia Carapcea, a principal program manager on the Cognitive Services team, and helped her team create a more robust dataset “that held us accountable across skin tones.”

Beyond technical challenges

Ece Kamar is a senior researcher in Microsoft’s research lab in Redmond, Washington. Her research focuses on AI tools that help engineers identify blind spots in training data, such as the underrepresentation of darker skinned women that may lead to AI systems with unacceptable error rates on gender classification tasks.

She said that improving the performance of the gender classifier in the Face API was mainly a technical challenge. “Collecting more data that captures the diversity of our world and being careful about how to measure performance are important steps toward mitigating these issues,” she said.

A more nuanced challenge, she said, is learning how, and when, to go in and mitigate AI systems that reflect and amplify societal biases not because of dataset incompleteness or algorithmic inadequacies, but because human societies are biased.

“If we are training machine learning systems to mimic decisions made in a biased society, using data generated by that society, then those systems will necessarily reproduce its biases,” explained Wallach.

Wallach’s team is developing best practices for the detection and mitigation of bias and unfairness along the entire development pipeline of these types of AI-powered products and services, from idea creation and data collection to model training, deployment and monitoring.

“This is an opportunity to really think about what values we are reflecting in our systems,” said Wallach, “and whether they are the values we want to be reflecting in our systems.”

Searching to find answers

For example, if you do a web search for the word “CEO,” chances are you’ll get information about the senior leadership position in companies and organizations around the world, including a handful of images – most likely of men.

That’s not surprising, since less than 5 percent of Fortune 500 CEOs are women.

At Microsoft, that’s prompted an ongoing exploration among engineers at the search engine Bing, in collaboration with experts such as Wallach, that is looking at how best to also surface results that reflect the active discussion in boardrooms, throughout academia and on social media about the dearth of female CEOs – and the efforts to change that.

“When we think about this kind of bias, we start to think about how do we educate our users on the bias, how do we explain to users what is going on in society and how do we potentially help users explore those things,” said Michael Golebiewski, a principal program manager on the Bing team.

“It is an area where we don’t have all the answers yet. It is an area where we are starting to think about how we have those conversations with the user as they are searching.”
Click to expand...

Source: Microsoft improves facial recognition to perform well across all skin tones, genders

Brink · Jun 10, 2022

Microsoft improves facial recognition ability to recognize gender

Microsoft announced Tuesday that it has updated its facial recognition technology with significant improvements in the system’s ability to recognize gender across skin tones.

That improvement addresses recent concerns that commercially available facial recognition technologies more accurately recognized gender of people with lighter skin tones than darker skin tones, and that they performed best on males with lighter skin and worst on females with darker skin.

With the new improvements, Microsoft said it was able to reduce the error rates for men and women with darker skin by up to 20 times. For all women, the company said the error rates were reduced by nine times. Overall, the company said that, with these improvements, they were able to significantly reduce accuracy differences across the demographics.

The higher error rates on females with darker skin highlights an industrywide challenge: Artificial intelligence technologies are only as good as the data used to train them. If a facial recognition system is to perform well across all people, the training dataset needs to represent a diversity of skin tones as well as factors such as hairstyle, jewelry and eyewear.

The team responsible for the development of facial recognition technology at Microsoft, which is available to customers as the Face API via Azure Cognitive Services, worked with experts on bias and fairness across Microsoft to improve a system called the gender classifier, focusing specifically on getting better results for all skin tones.

The Face API team made three major changes. They expanded and revised training and benchmark datasets, launched new data collection efforts to further improve the training data by focusing specifically on skin tone, gender and age, and improved the classifier to produce higher precision results.

“We had conversations about different ways to detect bias and operationalize fairness. We talked about data collection efforts to diversify the training data. We talked about different strategies to internally test our systems before we deploy them,” said Hanna Wallach, a senior researcher in Microsoft’s New York research lab and an expert on fairness, accountability and transparency in AI systems.

Wallach and her colleagues provided “a more nuanced understanding of bias,” said Cornelia Carapcea, a principal program manager on the Cognitive Services team, and helped her team create a more robust dataset “that held us accountable across skin tones.”

Beyond technical challenges

Ece Kamar is a senior researcher in Microsoft’s research lab in Redmond, Washington. Her research focuses on AI tools that help engineers identify blind spots in training data, such as the underrepresentation of darker skinned women that may lead to AI systems with unacceptable error rates on gender classification tasks.

She said that improving the performance of the gender classifier in the Face API was mainly a technical challenge. “Collecting more data that captures the diversity of our world and being careful about how to measure performance are important steps toward mitigating these issues,” she said.

A more nuanced challenge, she said, is learning how, and when, to go in and mitigate AI systems that reflect and amplify societal biases not because of dataset incompleteness or algorithmic inadequacies, but because human societies are biased.

“If we are training machine learning systems to mimic decisions made in a biased society, using data generated by that society, then those systems will necessarily reproduce its biases,” explained Wallach.

Wallach’s team is developing best practices for the detection and mitigation of bias and unfairness along the entire development pipeline of these types of AI-powered products and services, from idea creation and data collection to model training, deployment and monitoring.

“This is an opportunity to really think about what values we are reflecting in our systems,” said Wallach, “and whether they are the values we want to be reflecting in our systems.”

Searching to find answers

For example, if you do a web search for the word “CEO,” chances are you’ll get information about the senior leadership position in companies and organizations around the world, including a handful of images – most likely of men.

That’s not surprising, since less than 5 percent of Fortune 500 CEOs are women.

At Microsoft, that’s prompted an ongoing exploration among engineers at the search engine Bing, in collaboration with experts such as Wallach, that is looking at how best to also surface results that reflect the active discussion in boardrooms, throughout academia and on social media about the dearth of female CEOs – and the efforts to change that.

“When we think about this kind of bias, we start to think about how do we educate our users on the bias, how do we explain to users what is going on in society and how do we potentially help users explore those things,” said Michael Golebiewski, a principal program manager on the Bing team.

“It is an area where we don’t have all the answers yet. It is an area where we are starting to think about how we have those conversations with the user as they are searching.”
Click to expand...

Source: Microsoft improves facial recognition to perform well across all skin tones, genders

Windows 10: Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different...

Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different...

Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different...

Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different...

Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different... - Similar Threads - Face API Facial

My Facial Recognition-Microsoft Azure Cognitive Services Showing different confidence score

My Facial Recognition-Microsoft Azure Cognitive Services Showing different confidence score

My Facial Recognition-Microsoft Azure Cognitive Services Showing different confidence score

Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different...

Face API - Facial Recognition-Microsoft Azure Cognitive Services Showing different...

How to use facial recognition with face mask?

How to use facial recognition with face mask?

Different Facial Authentication services

Cognitive Services APIs: Vision