We’ve all experienced the terrible feeling of jolting awake after our blaring alarm clocks force us into consciousness. For the hearing-impaired, a blaring alarm clock usually means an intrusive and uncomfortable vibrating wristband. What if there were a better way to wake? Blu Vision is a visual alarm clock that uses blue light to gradually wake you up, adjusting its intensity by learning user behavior through the Clarifai API.

Blue light has a reputation as the light that’s “better than coffee.” Research has confirmed that blue light can actually improve our cognitive abilities, including memory, alertness, reaction time, and executive function. So, what better way to wake up than by the gradual brightening of blue light? Blu Vision is a visual alarm clock for the hearing-impaired that uses blue light and Clarifai’s API to deliver a more pleasant and healthy waking.

Blu Vision adjusts intensity by learning user behavior, and the only way to turn it off is by getting out of bed and making a gesture to a camera running the best image recognition software in the world – Clarifai’s API.


We love any hack that improves quality of life. We also love the creative use of the Clarifai API to turn off the alarm – now, if only someone would make an alarm that would cook us bacon when we wake up, too. Oh wait, that’s a thing. Read more about Blu Vision on DevPost!


We caught up with Kheng Wei Ang from Malaysia to ask him how he and his team at Dubhacks came up with the idea for Blu Vision and went about building it.

Clarifai: What inspired your idea for Blu Vision?

Kheng Wei: My friend Navid worked on SignAloud, which is a glove that translates sign language into speech and won the MIT-Lemelson prize. It also helps that Trevor has an annoying roommate that doesn’t turn off his alarm clock for hours.

What tools and languages did you use to build the app?

We used Java, Python and C++. We brought a lot of hardware to Dubhacks, including many Arduinos, RGB LEDs, and a solder iron. In the end, we have a Raspberry Pi running as a server which communicates to the Arduino that in turn trigger the LEDs. We faced many challenges such as the devices not communicating with each other, unfamiliarity with a new programming language, and time constraints especially with the fact that we’re dealing with hardware. We also did not have much time to train Clarifai’s software to recognize a thumbs up gesture, but it works fairly well during demonstration.

What was the best part about working with the Clarifai API?

It was definitely fun! Andrew enjoyed working with Cassidy (Clarifai’s developer evangelist), and got the image recognition software to run on our hardware in just a few hours. It was the first hackathon for Jason, Andrew and I, and the second for Trevor, and we managed to build a device that turns off by recognizing gestures. Friends thought that we were cool, but that’s Clarifai’s API being cool. That is proof of how easy it is!

Thanks for sharing, Blu Vision team!

To learn more, check out our documentation and sign-up for a free Clarifai account to start using our API – all it takes is three lines of code to get up and running! We’re super excited to share all the cool things built by our developer community, so don’t forget to tweet @Clarifai to show us your apps.

And give Kheng Wei, Trevor, Jason, and Andrew some props in the comments below. Until next time!