Color Documents on the Web with DJVU

We present a new image compression technique called DjVu" that is speci cally geared towards the compression of scanned documents in color at high resolution. With DjVu, a magazine page in color at 300dpi typically occupies between 40KB and 80KB, approximately 5 to 10 times better than JPEG for a similar level of readability. Using a combination of Hidden Markov Model techniques and MDL-driven heursitics, DjVu rst classi es each pixel in the image as either foreground text, drawings or background pictures, photos, paper texture. The pixel categories form a bitonal image which is compressed using a pattern matching technique that takes advantage of the similarities between character shapes. A progessive, wavelet-based compression technique, combined with a masking algorithm, is then used to compress the foreground and background images at lower resolution while minimizing the number of bits spent on the pixels that are not visible in the foreground and background planes. Encoders,...

• Type: Conference
• Year: 1999
• Where: ICIP
• Authors: Bill Riemers, Léon Bottou, Pascal Vincent, Patrick Haffner, Paul G. Howard, Yann LeCun
• Keywords: ICIP 1999, Image Processing, Pattern Matching Technique, Technique Called Djvu, Wavelet-based Compression Technique