Linux Containers Authors: Yeshim Deniz, Zakia Bouachraoui, Elizabeth White, Pat Romanski, Liz McMillan

Related Topics: Java IoT, Microservices Expo, Linux Containers

Java IoT: Article

Java Breakthrough: Code That Helps Blind People To Read Maps

Cornell Student Ankur Moitra Uses Java to Write Pioneering Image-to-Sound Software

Take Java computer code that can translate images into sound, via a rudimentary software program capable of converting pixels of various colors into piano notes of various tones, and what you have is a technology that enables blind people to read maps.

Victor K. Wong, a Cornell University graduate student from Hong Kong who lost his sight in a road accident at age seven, is helping to develop innovative software that translates color into sound. "Color is something that does not exist in the world of a blind person," explains Wong. "I could see before, so I know what it is. But there is no way that I can think of to give an exact idea of color to someone who has never seen before."

He helped develop the software in Cornell's Department of Electrical and Computer Engineering (ECE) with undergraduate engineering student Ankur Moitra and research associate James Ferwerda from the Program of Computer Graphics.

The inspiration for using image-to-sound software came in early 2004 when Wong realized his problems in reading color-scaled weather maps of the Earth's upper atmosphere - a task that is a necessary part of his doctoral work in Professor Mike Kelley's ECE research group.

It is a field dubbed "space weather," which attempts to predict weather patterns high over the equator for use by Global Positioning System and other satellite communications. A space weather map might show altitude in the vertical direction (along the "y" axis), time in the horizontal direction (along the "x" axis), and represent density with different colors.

As a scientist, Wong needs to know more than just the general shape of an image. He needs to explore minute fluctuations and discern the numerical values of the pixels so that he can create mathematical models that match the image. "Color is an extra dimension," explains Wong.

At first, the team tried everything from having Kelley verbally describe the maps to Wong to attempting to print the maps in Braille. When none of those methods provided the detail and resolution Wong needed, he and Ferwerda began investigating software. Moitra later became their project programmer."We started with the basic research question of how to represent a detailed color-scaled image to someone who is blind," recalls Ferwerda. "The most natural approach was to try sound, since color and pitch can be directly related and sensitivity to changes in pitch is quite good."

Over the summer of 2004, Moitra wrote a Java routine that could translate images into sound, and in August he unveiled a rudimentary software program capable of converting pixels of various colors into piano notes of various tones.

Wong test-drove the software by exploring a color photograph of a parrot. He used a rectangular Wacom tablet and stylus - a computer input device used as an alternative to the mouse - which gives an absolute reference to the computer screen, with the bottom left-hand corner of the tablet always corresponding to the bottom left-hand corner of the screen.

As Wong guided the stylus about the tablet, piano notes began to sing out. The full range of keys on a piano was employed, allowing color resolution in 88 gradations, ranging from blue for the lowest notes to red for the highest.

The software also has an image-to-speech feature that reads aloud the numerical values of the x and y coordinates as well as the value associated with a color at any given point on the image. "In principle I could turn off the music and just have the software read out the value of each point. I would know what the gradient is in a more absolute sense, but it would get annoying after some time. It keeps reading out 200.1, 200.8, 200.5, and so on," says Wong.

One of the biggest challenges of the project is the so-called "land-and-sea" problem. "Sometimes I just want to know where is the land and where is the sea," says Wong - meaning that he would like to have an idea where the major boundaries in an image lie, such as the boundary between the parrot and the background. The problem hinges on shape recognition, which for Wong can be difficult.

In the simplest situation, the right half of an image would be completely blue and the left half completely red. To find the boundary Wong has to move the stylus continuously back and forth from one color to the next along the length of the tablet, which is both time-consuming and error prone.

To solve the land-and-sea problem, Wong, Moitra and Ferwerda tried printing the major boundary lines of an image in Braille and then laying the printed sheet over the Wacom tablet, combining both audio and tactile detection. However, they are still working to develop software that can effectively pick out the important boundaries in an image so that it can be printed.

"It is also important that there is no time delay between notes," says Moitra. "That is something we need to improve. Otherwise the image will become shifted and distorted in Victor's mind."

One of the major issues facing the project is funding. "The initial work was done on a shoestring as a side project to grants Kelley and I have received," says Ferwerda, who is preparing a proposal to the National Science Foundation to extend this work and explore other ideas for making images and other technical content accessible to blind scientists and engineers.

Says Wong: "Tackling complex color images is only one problem out of many that blind scientists are facing. But I think this is a pretty important idea."

More Stories By Java News Desk

JDJ News Desk monitors the world of Java to present IT professionals with updates on technology advances, business trends, new products and standards in the Java and i-technology space.

Comments (11) View Comments

Share your thoughts on this story.

Add your comment
You must be signed in to add a comment. Sign-in | Register

In accordance with our Comment Policy, we encourage comments that are on topic, relevant and to-the-point. We will remove comments that include profanity, personal attacks, racial slurs, threats of violence, or other inappropriate material that violates our Terms and Conditions, and will block users who make repeated violations. We ask all readers to expect diversity of opinion and to treat one another with dignity and respect.

Most Recent Comments
Agreed 03/17/05 02:21:48 AM EST

}}} My assumption is that the blind would have increased sensitivity and perception of sound, so it may not be so difficult as I imagine. {{{

That's the key to it I think.

digitalchinky 03/16/05 08:25:11 PM EST

Not that I mind, but my slashdot comment was posted here? - it is unedited and in full, so no issue. The content is factual, if only a little vague. I was making reference to the black-knight dictionary scanners - or rather a sister system that does image recognition. The code base is similar to that of fingerprint recognition software - the downside is (still) that the machine needs to have a database of known entries to work with.

I think it'd be fairly easy to raster an image with sound, though resolution would be dependant on the short term memory of the user. Learning such a system would take quite some effort - morse code at 25wpm took 44 weeks at 8 hours per day (military) Even then it took another two years for it to become automatic (like driving a car)

My assumption is that the blind would have increased sensitivity and perception of sound, so it may not be so difficult as I imagine.

Mike L 02/14/05 02:53:03 PM EST

I was thinking that maybe higher notes be associated with blue instead of red. I think this would make more intuitive sense since red EM wavelengths are very long, while blue/UV are very short. I've also heard of people (not necessaririly blind) that can 'hear' colour, and associate low sounds with red and high with blue.

Maybe it should be optional, if not default, to change the direction that sound is associated with colour. It might even help for this sort of thing to catch on if there was a standardized sound/colour scheme that corresponded to the actual EM wavelenghts of visible light...

Lincoln 01/31/05 12:36:21 PM EST

Is there a demo online? I'd like to see it in action.

Jerry Davison 01/31/05 10:09:25 AM EST

This technology could be reversed and used to translate music into pictures for the deaf.

Paul Gbiby 01/28/05 03:28:53 PM EST

What's really interesting, though, is what is going on in Victor's mind as he processes his exploration of the pictures -- how he makes sense of the piano notes.

Glock27 01/27/05 07:29:10 AM EST

Java is being used for lots of interesting, cutting edge software projects. Freenet, speech recognition, game development, many Apache projects, Azureus...there are plenty of cool Java packages out there.

The fact is that the industry was badly in need of a sane replacement for C++. Java hit that niche quite nicely, and that accounts for its popularity.

error629 01/27/05 07:18:40 AM EST

Can't be any worse than http://video.google.com , which reads hastily typed subtitles. It can be amusing. :)

art6217 01/27/05 07:10:45 AM EST

Sound might be a very important way to convey images, either an additional one to textures, or replacing the textures completely. It may instantly inform about the kind of a surface. Sound might also convey edges, but then there is a problem of detecting edges: it is usually easy if the map is in a vector form, but in the case of general raster images a good edge detector or even a human that would mark the edges might be needed.

Lars Westergren 01/27/05 07:06:57 AM EST

My previous job was at the Swedish national library for the blind/visually disabled. Their lives have gotten a LOT easier with technology, and especially the net, but there are still lots of problems.

The greatest service you can do to them is make sure all web pages you make are HTML 4.01 compliant though. Alt tags for pictures are of course important (even if it just saying "logo"), and screen reader programs are not as forgiving as IE/Mozilla/Firefox et al when it comes to confusing tags.

digitalchinky 01/27/05 07:05:38 AM EST

I remember seeing a few 'black boxes' (Sparc 20's to be vaguely specific) that were running some fairly interesting algorithms (around the 1997/98 ish era) that would identify logo's from various transmissions, mostly faxes, thus identifying the sending entity.

It was more miss than hit, though I'm sure the recognition software has improved since then, it still relied upon a mathmatic description of the original image, much the same as a voice print.

IoT & Smart Cities Stories
CloudEXPO New York 2018, colocated with DXWorldEXPO New York 2018 will be held November 11-13, 2018, in New York City and will bring together Cloud Computing, FinTech and Blockchain, Digital Transformation, Big Data, Internet of Things, DevOps, AI, Machine Learning and WebRTC to one location.
Bill Schmarzo, Tech Chair of "Big Data | Analytics" of upcoming CloudEXPO | DXWorldEXPO New York (November 12-13, 2018, New York City) today announced the outline and schedule of the track. "The track has been designed in experience/degree order," said Schmarzo. "So, that folks who attend the entire track can leave the conference with some of the skills necessary to get their work done when they get back to their offices. It actually ties back to some work that I'm doing at the University of San...
Andrew Keys is Co-Founder of ConsenSys Enterprise. He comes to ConsenSys Enterprise with capital markets, technology and entrepreneurial experience. Previously, he worked for UBS investment bank in equities analysis. Later, he was responsible for the creation and distribution of life settlement products to hedge funds and investment banks. After, he co-founded a revenue cycle management company where he learned about Bitcoin and eventually Ethereal. Andrew's role at ConsenSys Enterprise is a mul...
IoT is rapidly becoming mainstream as more and more investments are made into the platforms and technology. As this movement continues to expand and gain momentum it creates a massive wall of noise that can be difficult to sift through. Unfortunately, this inevitably makes IoT less approachable for people to get started with and can hamper efforts to integrate this key technology into your own portfolio. There are so many connected products already in place today with many hundreds more on the h...
DXWorldEXPO | CloudEXPO are the world's most influential, independent events where Cloud Computing was coined and where technology buyers and vendors meet to experience and discuss the big picture of Digital Transformation and all of the strategies, tactics, and tools they need to realize their goals. Sponsors of DXWorldEXPO | CloudEXPO benefit from unmatched branding, profile building and lead generation opportunities.
DXWorldEXPO LLC announced today that Telecom Reseller has been named "Media Sponsor" of CloudEXPO | DXWorldEXPO 2018 New York, which will take place on November 11-13, 2018 in New York City, NY. Telecom Reseller reports on Unified Communications, UCaaS, BPaaS for enterprise and SMBs. They report extensively on both customer premises based solutions such as IP-PBX as well as cloud based and hosted platforms.
In his keynote at 19th Cloud Expo, Sheng Liang, co-founder and CEO of Rancher Labs, discussed the technological advances and new business opportunities created by the rapid adoption of containers. With the success of Amazon Web Services (AWS) and various open source technologies used to build private clouds, cloud computing has become an essential component of IT strategy. However, users continue to face challenges in implementing clouds, as older technologies evolve and newer ones like Docker c...
The best way to leverage your Cloud Expo presence as a sponsor and exhibitor is to plan your news announcements around our events. The press covering Cloud Expo and @ThingsExpo will have access to these releases and will amplify your news announcements. More than two dozen Cloud companies either set deals at our shows or have announced their mergers and acquisitions at Cloud Expo. Product announcements during our show provide your company with the most reach through our targeted audiences.
To Really Work for Enterprises, MultiCloud Adoption Requires Far Better and Inclusive Cloud Monitoring and Cost Management … But How? Overwhelmingly, even as enterprises have adopted cloud computing and are expanding to multi-cloud computing, IT leaders remain concerned about how to monitor, manage and control costs across hybrid and multi-cloud deployments. It’s clear that traditional IT monitoring and management approaches, designed after all for on-premises data centers, are falling short in ...
The deluge of IoT sensor data collected from connected devices and the powerful AI required to make that data actionable are giving rise to a hybrid ecosystem in which cloud, on-prem and edge processes become interweaved. Attendees will learn how emerging composable infrastructure solutions deliver the adaptive architecture needed to manage this new data reality. Machine learning algorithms can better anticipate data storms and automate resources to support surges, including fully scalable GPU-c...