Anurag Bhandari

Accessify: An ML Powered Application to Provide Accessible Images on Web Sites

Web Accessibility remains a major concern of the rapidly growing Internet community. Accessing online content is crucial for many people as they engage in a variety of tasks every day. Content can be in any form, such as audio, video, images and text. A major portion of a websites viewport generally contains images, and there are set standards & guidelines for providing information about these images while creating image elements on a webpage. Yet, most websites do not strictly follow accessibility guidelines and, as a result, either a website contains no descriptions of images or the descriptions provided are not sufficient to convey the meaning to visually impaired people who use screen readers for accessing web content. In this paper, we propose a solution that provides alternate image descriptions to all images on a website with help of Machine Learning in a completely unobtrusive environment. The application does not require any setup and can be used on static as well as dynamic websites.

Building Smarter Applications Using Cognitive APIs

The famous saying “Rome wasn’t built in a day” is so true about Microsoft cognitive services. Each service is exposed as a RESTful API by abstracting years and decades of experience, complex algorithms, deep neural networks, fuzzy logic, and research from the Microsoft research team. In Chapter 4, you were introduced to Microsoft Cognitive Services. You also learned how cognitive services are different from traditional programming systems. Later in Chapter 4, you got a sneak preview of all the Microsoft Cognitive Services API that Microsoft has produced.

Making Predictions with Machine Learning

Our adventures in AI 2.0 are nearing their conclusion. If you have gone through all of the previous nine chapters, you have almost all the skills needed to build the next generation of smart applications. You are almost AI 2.0 ready. Almost.

The Artificial Intelligence 2.0 Revolution

Once upon a time, computers were as big as rooms. They were capable of complex mathematical calculations. They were not, though, meant to be operated by people like me and you. Nor were they designed for creating documents and presentations, playing games, or surfing the web. Early computers were powered by vacuum tubes—just like most other sophisticated electronic devices of the time—and were used in scientific research. Then, the semiconductor revolution happened, and the transistor was born.

Implementing Blockchain as a Service

In the last chapter, you learned about the emergence of Blockchain and the very core reason for building Blockchain was cryptocurrency, especially Bitcoin. Over the years, various industry verticals started using Blockchain technology for non-payment systems. As we mentioned in the previous chapter, Blockchain changes the way we trust. While writing this book, various industries across verticals are transforming their individual business cases with the power of Blockchain. Every day new use cases are getting evolved on how Blockchain technology can transform a specific vertical. There is absolutely no denial of the fact that Blockchain is going to disrupt every vertical in the very massive way that one can imagine and would be the source of the next industrial revolution.

Creating Smart IoT Applications

In Chapter 2 we learned about the Internet of Things, IoT devices, practical use cases, and messaging protocols. We also gained the conceptual understanding of Azure IoT Suite and its various components, especially Azure IoT Hub. Armed with this knowledge, it is time to create an IoT solution ourselves. We will create our own IoT network and write applications for devices in that network to solve a real-world problem.

Capturing, Analyzing, and Visualizing Real-Time Data

Having come this far, you are now equipped with the knowledge of how to create next generation AI 2.0 applications. In your arsenal, you have weapons, such as Cognitive Services, IoT Hub, and Blockchain, to help you create truly cutting-edge intelligent solutions for clients, customers, or your own organization. From a developer’s perspective, you are fully equipped. However, developing solutions is only part of a bigger picture, no matter how big it is.

Consuming Microsoft Cognitive APIs

By now, you have a fair understanding of Microsoft Cognitive technologies, its various offerings in terms of service, and a sneak preview of understanding their concepts. Microsoft has done a fantastic job in abstracting the research on AI and machine learning, hiding all complex processing nuances by giving easy-to-consume REST based services, sitting on its Azure Cloud solution. In fact, the entire suite of Microsoft Cognitive Services is exposed as REST APIs. Since the REST API has an API endpoint, you really don’t need any specific platform or programming language to consume it. Another advantage of the REST API is that it can accept input in JSON or XML format and give output in the same formats. This gives you great flexibility to consume REST API directly in all major programming languages, such as C#, Java, PHP, Ruby, Python, JavaScript, and so on. As this book targets .NET developers, we will restrict ourselves to using C# throughout the book. But, really, the fundamentals of consuming Microsoft Cognitive Services remain the same for any language.

Understanding Cognitive APIs

By now, you are conversant with IoT and have a good understanding of creating a smart application using IoT. Chapter 1 started by introducing your journey to the world of artificial intelligence. As discussed in the previous chapters, we are presently in the first AI revolution, which marks the inception of AI-as a service. What comes to your mind when you hear the term artificial intelligence. Scary robots? A topic of sophisticated research? A future of machines that can do complex tasks with a blink of an eye? Normally, developers think of AI implementation as a tough task involving writing complex algorithms and writing hundreds of lines of code. Consider the following conversation:

Understanding the Internet of Things and Azure IoT Suite

A few years ago, Internet of Things (IoT) was an emerging trend. Today, it is part of modern arsenal of IT solutions. In the consumer space, IoT is generally perceived as smartwatches, fridges, TVs, etc.—age-old things that are now connected to the Internet. It is seen more as a convenience feature than a solution to an existing problem (smart thermostats and remote pet food dispensers, anyone?).