Browsing through high quality document images with DjVu

Patrick Haffner; Leon Bottou; Paul G. Howard; Patrice Simard; Yoshua Bengio; Yann Le Cun

Browsing through high quality document images with DjVu

Patrick Haffner, Leon Bottou, Paul G. Howard, Patrice Simard, Yoshua Bengio, Yann Le Cun

Computer Science

Research output: Contribution to conference › Paper

Abstract

We present a new image compression technique called `DjVu' that is specifically geared towards the compression of high-resolution, high-quality images of scanned documents in color. With DjVu, any screen connected to the Internet can access and display images of scanned pages while faithfully reproducing the font, color, drawing, pictures, and paper texture. A typical magazine page in color at 300 dpi can be compressed down to between 40 to 60 KB, approximately 5 to 10 times better than JPEG for a similar level of subjective quality. B&W documents are typically 15 to 30 KBytes at 300 dpi, or 4 to 8 times better than CCITT0G4. A real-time, memory efficient version of the decoder was implemented, and is available as a plug-in for popular web browsers.

Original language	English (US)
Pages	309-318
Number of pages	10
State	Published - 1998
Event	Proceedings of the 1998 IEEE Forum on Research and Technology Advances in Digital Libraries, IEEE ADL'98 - Santa Barbara, CA, USA Duration: Apr 22 1998 → Apr 24 1998

Other

Other	Proceedings of the 1998 IEEE Forum on Research and Technology Advances in Digital Libraries, IEEE ADL'98
City	Santa Barbara, CA, USA
Period	4/22/98 → 4/24/98

ASJC Scopus subject areas

Management of Technology and Innovation

Access to Document

Fingerprint Dive into the research topics of 'Browsing through high quality document images with DjVu'. Together they form a unique fingerprint.

Cite this

Haffner, P., Bottou, L., Howard, P. G., Simard, P., Bengio, Y., & Cun, Y. L. (1998). Browsing through high quality document images with DjVu. 309-318. Paper presented at Proceedings of the 1998 IEEE Forum on Research and Technology Advances in Digital Libraries, IEEE ADL'98, Santa Barbara, CA, USA, .

Browsing through high quality document images with DjVu. / Haffner, Patrick; Bottou, Leon; Howard, Paul G.; Simard, Patrice; Bengio, Yoshua; Cun, Yann Le.

1998. 309-318 Paper presented at Proceedings of the 1998 IEEE Forum on Research and Technology Advances in Digital Libraries, IEEE ADL'98, Santa Barbara, CA, USA, .

Research output: Contribution to conference › Paper

@conference{00a681f372d74a4eb1eed8617b7a3f25,

title = "Browsing through high quality document images with DjVu",

abstract = "We present a new image compression technique called `DjVu' that is specifically geared towards the compression of high-resolution, high-quality images of scanned documents in color. With DjVu, any screen connected to the Internet can access and display images of scanned pages while faithfully reproducing the font, color, drawing, pictures, and paper texture. A typical magazine page in color at 300 dpi can be compressed down to between 40 to 60 KB, approximately 5 to 10 times better than JPEG for a similar level of subjective quality. B&W documents are typically 15 to 30 KBytes at 300 dpi, or 4 to 8 times better than CCITT0G4. A real-time, memory efficient version of the decoder was implemented, and is available as a plug-in for popular web browsers.",

author = "Patrick Haffner and Leon Bottou and Howard, {Paul G.} and Patrice Simard and Yoshua Bengio and Cun, {Yann Le}",

year = "1998",

language = "English (US)",

pages = "309--318",

note = "Proceedings of the 1998 IEEE Forum on Research and Technology Advances in Digital Libraries, IEEE ADL'98 ; Conference date: 22-04-1998 Through 24-04-1998",

}

TY - CONF

T1 - Browsing through high quality document images with DjVu

AU - Haffner, Patrick

AU - Bottou, Leon

AU - Howard, Paul G.

AU - Simard, Patrice

AU - Bengio, Yoshua

AU - Cun, Yann Le

PY - 1998

Y1 - 1998

N2 - We present a new image compression technique called `DjVu' that is specifically geared towards the compression of high-resolution, high-quality images of scanned documents in color. With DjVu, any screen connected to the Internet can access and display images of scanned pages while faithfully reproducing the font, color, drawing, pictures, and paper texture. A typical magazine page in color at 300 dpi can be compressed down to between 40 to 60 KB, approximately 5 to 10 times better than JPEG for a similar level of subjective quality. B&W documents are typically 15 to 30 KBytes at 300 dpi, or 4 to 8 times better than CCITT0G4. A real-time, memory efficient version of the decoder was implemented, and is available as a plug-in for popular web browsers.

AB - We present a new image compression technique called `DjVu' that is specifically geared towards the compression of high-resolution, high-quality images of scanned documents in color. With DjVu, any screen connected to the Internet can access and display images of scanned pages while faithfully reproducing the font, color, drawing, pictures, and paper texture. A typical magazine page in color at 300 dpi can be compressed down to between 40 to 60 KB, approximately 5 to 10 times better than JPEG for a similar level of subjective quality. B&W documents are typically 15 to 30 KBytes at 300 dpi, or 4 to 8 times better than CCITT0G4. A real-time, memory efficient version of the decoder was implemented, and is available as a plug-in for popular web browsers.

UR - http://www.scopus.com/inward/record.url?scp=0031700336&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031700336&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0031700336

SP - 309

EP - 318

T2 - Proceedings of the 1998 IEEE Forum on Research and Technology Advances in Digital Libraries, IEEE ADL'98

Y2 - 22 April 1998 through 24 April 1998

ER -