Hiroki Kanno

TL;DR: In this article, the authors detect the features of the document, such as the top, bottom, left and right margins, the character space, the line space, word space, column space, size and coordinates of each character, and the like.

TL;DR: In this article, a system and a method for providing characteristic data associated with a scanned document is provided. The method includes analyzing a bitmapped image file of a document, determining at least one characteristic data of the document, and linking the characteristic data to the image file, wherein the document is useable by a document management system to identify the document in a search.

TL;DR: In this paper, the maximum density difference of an image within a predetermined range is calculated as a feature amount, and a quantization error of pixels around a pixel of interest is calculated, and then, a correction amount is calculated by proportionally distributing the quantization errors in accordance with the feature amount calculated by a feature amounts calculator.

TL;DR: In this paper, an image processor includes an image input unit for reading and inputting an image of a document, an image output unit for outputting the image processed by the image processing unit.

TL;DR: In this paper, a first compressing section which compresses each block of an image into first compressed data, a first code converting section which converts the first compressed dataset into second compressed dataset, a second code converting segmentation section which transforms the second dataset into third dataset and a decoding section which decodes the third dataset.