Channels ▼
RSS

Parallel

Designing the Intel Reader


Selecting the Computing Environment

From our architectural exploration, it became clear that the Intel Reader must be based on a highly flexible platform. Several different vendors have developed OCR and text-to-speech algorithms for different languages, and additional languages are being added each year. In order to take advantage of this continuous improvement in the OCR and text-to-speech environments, the Intel Reader needs a highly flexible computing environment.

In addition to flexibility, the processor must provide sufficient performance to complete the OCR algorithm within a reasonable delay. However, the size and power consumption must be low enough to fit with the required hand-held form-factor.

The Intel Atom processor and its associated chipsets running a general-purpose Linux operating system like Moblin provides this type of flexibility, performance, power consumption, and size. The Intel Atom processor is an X86 compatible processor with operating speeds above 1 GHz.

Conclusion

When developing technology to help people with disabilities become more independent, developers face a dilemma: if they tailor the use too tightly, the number of potential users is reduced to the point that the device is not economically sustainable. On the other hand, if they keep the feature set too broad, it fails to address the needs of any one community. In short, narrow designs fail for lack of a market, and broad designs fail for lack of use. The Intel Reader is an attempt to navigate this design challenge. The core usage model, reading text from a page with a camera and converting it to speech, addresses a need shared by blind, low-vision, and dyslexic users. In this way, we are attempting to reframe the market from a subpopulation of people with one of these disabilities to a larger population, renamed as those with Print Disability.

We had to make choices, focusing on users with a basic set of technology literacy skills; for example, someone who might use a cell phone or communicate via e-mail. We also balanced the competing needs of seniors and teens and of the sighted and those with limited vision.

The Intel Reader can also be seen as a step on the road to the future of reading and writing. By 2020, we should expect to see a range of devices that will move content seamlessly between print, digital, and audio. Moreover, we should expect the cost of such technology to plummet. The key inflection point in the cost curve will be when this technology moves from a necessity for a disability population to a convenience for the general population. Crossing this line will drive economies of scale similar to other common communication and entertainment technologies. Where DVD players once cost over $1,000, they now cost under $50. Cell phones, once the toy of the very rich, are now included for free with a service contract. We expect that in the future, the evolution of the Intel Reader technology will follow a similar path. Indeed, we share a vision of this technology becoming a very low cost device, one that will serve the disabled population and the general population. It is in this moment of cross-over that we will see the true goal of the device come to fruition -- the establishment of an equal playing field for all people who want access to knowledge and increased independence.


This article and more on similar subjects may be found in the Intel Technology Journal, September 2009 Edition, "Enabling Healthcare in the Home". More information can be found at http://intel.com/technology/itj.


Related Reading


More Insights






Currently we allow the following HTML tags in comments:

Single tags

These tags can be used alone and don't need an ending tag.

<br> Defines a single line break

<hr> Defines a horizontal line

Matching tags

These require an ending tag - e.g. <i>italic text</i>

<a> Defines an anchor

<b> Defines bold text

<big> Defines big text

<blockquote> Defines a long quotation

<caption> Defines a table caption

<cite> Defines a citation

<code> Defines computer code text

<em> Defines emphasized text

<fieldset> Defines a border around elements in a form

<h1> This is heading 1

<h2> This is heading 2

<h3> This is heading 3

<h4> This is heading 4

<h5> This is heading 5

<h6> This is heading 6

<i> Defines italic text

<p> Defines a paragraph

<pre> Defines preformatted text

<q> Defines a short quotation

<samp> Defines sample computer code text

<small> Defines small text

<span> Defines a section in a document

<s> Defines strikethrough text

<strike> Defines strikethrough text

<strong> Defines strong text

<sub> Defines subscripted text

<sup> Defines superscripted text

<u> Defines underlined text

Dr. Dobb's encourages readers to engage in spirited, healthy debate, including taking us to task. However, Dr. Dobb's moderates all comments posted to our site, and reserves the right to modify or remove any content that it determines to be derogatory, offensive, inflammatory, vulgar, irrelevant/off-topic, racist or obvious marketing or spam. Dr. Dobb's further reserves the right to disable the profile of any commenter participating in said activities.

 
Disqus Tips To upload an avatar photo, first complete your Disqus profile. | View the list of supported HTML tags you can use to style comments. | Please read our commenting policy.
 

Video