Using Image Services from Azure and GCP to Enhance the Customer Experience
Today’s user experiences have started to require context, and are ultimately being changed by that context. In our real-time, connected world of devices, we are moving away from the standard task-oriented UX to the contextual UX, where we are now building systems and devices that learn and adapt to our needs in specific situations, locations, and context of use. Today’s technology allows us to weave a web of interconnected, simple, active and passive devices into more complex, adaptive systems that can meet users needs, be personalized and delivered based on real-time cues. A contextual UX is defined as the use of context-aware technologies that allow the design to be personalized to meet the unique needs of the individual user based off of the current situation.
To create a truly contextual UX experience, the system requires a way to see the user and be adaptive to their current needs. During one of my earlier projects at Slalom, I got the opportunity to create a contextual UX experience with no limitations, and the only requirement was that we used a camera to gather data about the customer. Once our team was assembled, we landed on a couple of different use cases that we wanted to show how using an image service from Azure and Google Cloud Platform could improve the customer experience.
The Scenarios:
- It’s a Saturday afternoon and you are out watching the game at one of your favorite restaurants wearing your lucky jersey. You walk to a beverage dispensing machine and upon making a selection, you notice that your team’s logo is now branding the menu. The current game store is up in the corner and you even see that your team has been to that machine more times than its rival.
2. A customer steps up to the optical-enabled machine and the sensor recognizes that the user is “grumpy”, the machine changes to a simpler, “classic” experience.
To implement the two scenarios described above, we ended up using Azure’s Computer Vision. This helps in identifying visual content in the images. Facilities like tagging, domain-specific models, and descriptions can identify content. In fact, this can recognize human faces, identify printed text and even generate descriptions. Some of the applications of Computer Vision include image classification, reading text in images, handwriting recognition, recognition of celebrities and landmarks, and optical character recognition (OCR). Azure’s Face, the vision API, can identify and recognize faces in pictures, saving a lot of time and effort. Some of the typical applications are face detection, emotion recognition, face identification, similar face recognition, and face grouping. We then used Google’s Logo detection API to return most widely recognized logos. We used a laptop with a webcam and a UWP app to register the results and control the UI.
Image services are super-intelligent APIs that let you release intelligent applications to your customers. Through this, you can create systems that can see, hear, speak and understand people in their own natural language and use the same communication method to relate to them. Using AI to implement facial recognition and other functionalities with a few lines of code make personalization and customization simpler. This will continue to grow, with computers thinking like the human brain, and machines becoming more than ready to be a part of daily life. Thus, incorporating Cognitive Services in your app becomes an important step to providing a better contextual UX experience.
