Color blindness (color vision deficiency or CVD) affects approximately 1 in 12 men and 1 in 200 women worldwide. It is caused by the absence or impairment of one or more cone cells within the human eye. Due to a deficiency in these cells' ability to detect certain wavelengths, the retina itself is unable to distinguish between these colors. The most common of these deficiencies is red-green color blindness, in which the individual has trouble distinguishing between the red and green wavelengths. Within this category, there are four types of color blindness: deuteranomaly (green-weak), deuteranopia (green-blind), protanomaly (red-weak), and protanopia (red-blind). Both protanopia and deuteranopia make the individual completely unable to differentiate between red and green.
The next most common form of color blindness is blue-yellow color blindness. People with this condition have difficulty distinguishing between the colors blue and green, as well as the colors yellow and red. Tritanomaly is the mild form of the condition and is characterized by the impairment of the relevant color receptors. Tritanopia is the more severe form and is characterized by the complete absence of the relevant color receptors, which makes it much more difficult to tell the difference between blue and green, purple and red, and yellow and pink.
Despite the large segment of the population affected by color blindness, many people do not realize the everyday struggles that color-blind people face. Color blindness impacts simple tasks such as the thorough cooking of meat (due to difficulty distinguishing between the color of cooked meat and uncooked meat), distinguishing between fresh and spoiled foods (such as moldy bread), distinguishing between ripe and unripe fruits, and choosing what clothes to wear. Color blindness also affects more complex tasks, such as painting, graphic design, or jobs involving colored wires much more difficult than they would be for those with normal color vision. Therefore, this tool, Hue Helper, will act as a simple tool that color-blind people can use to differentiate the colors of their surroundings, thus aiding them in accomplishing everyday tasks that so many people take for granted.
What it does
Hue Helper provides color correction for the three most common forms of color blindness: protanomaly/protanopia, deuteranomaly/deuteranopia, and tritanomaly/tritanopia. Although it cannot restore normal color vision to those who are color-blind, it can help them differentiate between colors in a way that they would not normally be able to.
In addition, Hue Helper provides simulations of protanopia and deuteranopia for the benefit of those with normal color vision. These simulations can be used by web developers, graphic designers, and others who are interested in creating products that are accessible to color-blind people.
How I built it
Both the color-blind correction filters as well as the color-blind simulation filters were created using lookup tables. The simulation filters use the same algorithm as Adobe Photoshop's colorblind simulation filters, while the color correction filters use the same algorithm as Google Chrome's inbuilt color filter schemes.
In addition, we added buttons in order to allow users to toggle between each type of filter.
Challenges I ran into
It was difficult to understand how to convert the images through use of the Daltonization algorithm. This was an obstacle because the Daltonization algorithm doesn’t work with the RGB model, which is the model used in the majority of all image processing algorithms. The Daltonization algorithm instead makes use of the Long-Medium-Short Waves (LMS) Color Space, a model that attempts to emulate the way in which our brains process the varying wavelengths of light.
Accomplishments that I'm proud of
The main obstacle of this project was overcoming the restrictions set by the Daltonization algorithm due to its incompatibility with standard RGB models. However, our team worked diligently to try and find a way to implement the algorithm into the LMS color space form that could be interpreted via Adobe Lightroom. This process did not go as smoothly as originally planned; however, these setbacks allowed us to be able to regroup and further refine our development schedule. While hectic over the course of the project we became closer and learned how to effectively communicate with each other. Overall, I am really proud of our ability to really come together and apply our different strengths towards a common goal.
What I learned
What's next for us
Augmented reality is an up and coming tool that while having many applications it is unfortunately limited by how early in its infancy it is currently in. While the idea of us catching a virtual monster or playing card games where our cards come to life is amazing in itself, the true potential of augmented reality lies in its use to enhance the human experience in our daily lives. The ability for AR to innovate the methods in which the future generations are able to learn at schools is limitless.What if our glasses came loaded with an AR tool that would allow electricians to view schematics in real time? What if surgeons could visualize a patient’s blood vessels in a 3-dimensional space prior to surgery based on imaging? This project attempts to act as a prosthetic, an emulation, for one of the most vital of human senses, sight. That is the overall goal of this project as well as the general goal of this group, to allow innovation in medicine to be married to innovation in coding. We are hopeful that this project inspires others to consider other ways we can help simplify the lives of those who suffer from various forms of health problems or deficiencies.