Technology has changed our lives. Be it online shopping or social media to interact with thousands of people at a time, technology always makes it easy. One such new technology is developed for people suffering from visual impairment, who can now equally enjoy the internet memes. This new technology will turn the Memes into audio for visually impaired users.
Completely or partially blind people can use social media through text to speech techniques. These people can listen to the news feed, check out the stories, and all those stuff that is possible to convert into the audio form. For describing images, they make use of ‘Alternate text’ but this technology doesn’t work in case of memes because these are the funny images and puns that do not have any Alt Text or Alternative Text.
But now visually impaired people can also enjoy and laugh aloud on Memes shared on social media. Researchers at Carnegie Mellon University developed a technique to recognize memes, add Alt Text to Memes applying prewritten templates, and make easy to understand to the listeners.
Memes are pictures that are perfectly suitable for the funny text written over it. They are hilarious and full of humor. Memes are extremely funny but can’t be enjoyed by the blind people. In this regard, Jeff Bigham, an associate professor in the Human-Computer Interaction Institute, said that “Memes may not seem like the most important problem, but a vital part of accessibility is not choosing for people what deserves their attention. Many people use memes, and so they should be made accessible.”
Most of the funny memes you can find are on social platforms like Facebook, Instagram, and Twitter but a few of them allow you to add Alternate text. And even if it allows, people hardly know about it or the option is not easily accessible. Disclosing the statistics of the research, CMU researchers have said that on an average out of the 9 Million tweets only 0.1 % tweeters add ‘Alt Text’ in the images.
For facilitating visually impaired people to enjoy memes, Cole Gleason, a Ph.D. student in CMU’s Human-Computer Interaction Institute (HCII.) said that memes can be described using fundamental computer vision technique. The technique here makes use of the OCR method to decipher the text written on the meme images. All it needs is a template for each type of meme which describes the image and text written on the image.
Adding to his statement on audio memes, Gleason has also said that not all the memes can be successfully converted into audios with this technique because some of the memes are hilarious only if you see them. So, it is an exception to this method. However, the technique is enough advanced to add up the music and sound along with the text to feel the humor better.
The report of this new technology has been presented at the ACCESS conference held at Pittsburgh. This research was conducted by a team of fellow researchers and students of HCII. These researchers are also working on other projects as well like, a browser extension for Twitter to add ‘Alt Text’ and integrate ‘Alt Text’ into the metadata of images.