Title :
A new bi-level quantizing method for document images
Author :
Kuwata, Naoki ; Murayama, Yasuhiko ; Ilno, S.
Author_Institution :
Seiko Epson Corp., Nagano, Japan
fDate :
8/1/1992 12:00:00 AM
Abstract :
An adaptive bilevel quantizing technique for images containing text and continuous-tone areas in the same page is proposed. At first, the original document image is divided into M×M pixel blocks and whether a block is a continuous-tone area or not is determined by using two features, the density of black pixels in the block and the differential value to neighbors. Then, continuous-tone areas are made binary by using the multistep dither matrix. Finally, the remaining area, which includes text and figures, is quantized to bilevel
Keywords :
document image processing; image processing; adaptive bilevel quantizing technique; black pixel density; continuous-tone areas; differential value; document images; multistep dither matrix; pixel blocks; Character recognition; Displays; Facsimile; Feature extraction; Image processing; Image resolution; Image segmentation; Pixel; Research and development;
Journal_Title :
Consumer Electronics, IEEE Transactions on