Titlebook: Structured Document Image Analysis; Henry S. Baird,Horst Bunke,Kazuhiko Yamamoto Book 1992 Springer-Verlag Berlin Heidelberg 1992 Computer

设想

High Quality Vectorization Based on a Generic Object Model regarded as the same thing as digitizing accuracy, which is evaluated in terms of the error between the original line-drawing and the resultant vector sequence. However, this accuracy does not always correspond to perceptual quality. Based on the discussion about possible distortions in a vectoriza

射手座

Towards the Understanding of Printed Documentscument analysis system. This interpretation of the term ‘understanding’ shall be explained a little more deeply. An attempt shall be made to clarify the important question: “Up to what level can a machine really understand a given document?” Looking at the many problems still unsolved, this is indeed questionable.

称赞

Analysis of Scanned Documents — a Syntactic Approacheen the various entity classes or blocks. Lexical and syntax analysis tools, Lex and Yacc, are used to segment and label the blocks. These block-grammars can be generated manually or from a parameter table. Further extensions involving multiple grammars and backtracking algorithms are also discussed.

潜移默化

palette

Recognition of Hand-Printed Chinese Characters and the Japanese Cursive Syllabaryes between pairs of the line segments in the dictionary and the input, and then iteration finds acceptable combinations of the matches. The system was trained and tested on the ETL8 database; recognition results were 99% correct on the “good quality” data set, and 94.6% on the “poor quality” data set.

逢迎春日

ticlopidine

omnibus

An Overview of Techniques for Graphics Recognition of succinct image interpretations. This paper is primarily survey in nature, but an effort is made to provide information to evaluate and compare techniques, both through reference to more focused articles, as well as through our own experience.

你敢命令

Engaging

A Top-Down Approach to the Analysis of Document Imagesare rectangular regions among which spatial constraints are defined without recursions. By matching such templates, input document images can be classified, and bibliographic items such as a title and author’s name can be extracted. Experiments have shown promising results and it can be applied to an automatic document filing system.