8103

A Braille Conversion Service Using GPU and Human Interaction by Computer Vision

Roman Graf, Reinhold Huber-Mork
Digital Memory Engineering Safety & Security Department, AIT Austrian Institute of Technology GmbH, Vienna, Austria
8th International Conference on Preservation of Digital Objects (iPRES 2011), 2011
@article{graf2012braille,

   title={A Braille Conversion Service Using GPU and Human Interaction by Computer Vision},

   author={Graf, R. and Huber-M{"o}rk, R.},

   year={2012}

}

Download Download (PDF)   View View   Source Source   

876

views

Scalable systems and services for preserving digital content became important technologies with increasing volumes of digitized data. This paper presents a new Braille converter service that is a sample implementation of scalable service for preserving digital content. The converter service facilitates complex conversion problems regarding Braille code. Braille code is a method which allows visually impaired people to read and write tactile text. Using a GPU with the CUDA architecture allows the creation of a parallel processing service with enhanced scalability. The Braille converter is a web service that provides automatic conversion from the older BRF to the newer PEF Braille format. This service can manage a large number of objects. Speedups on the order of magnitude of 5000 to 6900 (depending on the size of the object) were achieved using a GPU (GTX460 graphics card) with respect to a CPU implementation. An extension involving an image processing system is used for human interaction. Optical pattern recognition allows Braille code creation using Braille patterns. No special input device and skills are needed, only familiarity with Braille code is required.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

* * *

* * *

TwitterAPIExchange Object
(
    [oauth_access_token:TwitterAPIExchange:private] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
    [oauth_access_token_secret:TwitterAPIExchange:private] => o29ji3VLVmB6jASMqY8G7QZDCrdFmoTvCDNNUlb7s
    [consumer_key:TwitterAPIExchange:private] => TdQb63pho0ak9VevwMWpEgXAE
    [consumer_secret:TwitterAPIExchange:private] => Uq4rWz7nUnH1y6ab6uQ9xMk0KLcDrmckneEMdlq6G5E0jlQCFx
    [postfields:TwitterAPIExchange:private] => 
    [getfield:TwitterAPIExchange:private] => ?cursor=-1&screen_name=hgpu&skip_status=true&include_user_entities=false
    [oauth:protected] => Array
        (
            [oauth_consumer_key] => TdQb63pho0ak9VevwMWpEgXAE
            [oauth_nonce] => 1472410392
            [oauth_signature_method] => HMAC-SHA1
            [oauth_token] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
            [oauth_timestamp] => 1472410392
            [oauth_version] => 1.0
            [cursor] => -1
            [screen_name] => hgpu
            [skip_status] => true
            [include_user_entities] => false
            [oauth_signature] => UZpnJkFALS89jDfa4S99h8XaV5k=
        )

    [url] => https://api.twitter.com/1.1/users/show.json
)
Follow us on Facebook
Follow us on Twitter

HGPU group

1969 peoples are following HGPU @twitter

HGPU group © 2010-2016 hgpu.org

All rights belong to the respective authors

Contact us: