Ko Asai

Character Image Segmentation

In the Optical Character Reader (OCR) system design, the character segmentation technique is important. For example, the Automatic Mail Address Reader is required to manage printed characters of many font types and poor print quality. In this case, OCR performance will be affected by character segmentation technique. This paper describes two new methods for character segmentation under more general conditions. The character segmentation problem can be formulated and classified as a pitch estimation problem and a character sectioning decision problem. These problems are resolved by using a statistical analysis method based on least square error function and a dynamic programing method with the minimum variance for separation between candidate positions in a line image. The effectiveness of the proposed methods has been evaluated through actual mail address segmentation experiments.

Document Image Analysis For Reading Books

A fundamental problem in machine vision is to detect and identify special objects in an image. In the field of machine-reading for existing printed matter and books, a very important technique allows extracting and recognizing characters in desired text lines from a document image. This paper describes a hierarchical image segmentation, which separates a document image into its entities. Furthermore, a character segmentation, with minimum variance criterion, and a character recognition, based on three improved loci feature, have been developed as two elemental methods for reading books. In these experimental results using different commercial Japanese pocket books, 99% of text lines were correctly extracted. Also, it was successful in reading 99.30% of the Japanese characters and Chinese ideographs, as used in printed text.

Adaptive Character Segmentation Method Based on Minimum Variance Criterion

Character segmentation is a technique which separates individual characters from character line image. It is one of the most important prerequisites for character recognition. In the past, segmentation of individual characters from a general object, such as mailing address and existing document, had strong constraints imposed on the character segmentation. These included contact between adjacent characters and separation of a single character, thereby preventing the segmentation technique from being a systematic approach. This paper discusses character segmentation, an indispensable means of pre-processing in character recognition which has been considered to cope with the individual cases. A character segmentation method is proposed which is based on the clustering for the character cluster interval histogram by linear square-error function, and on the dynamic programming using the minimum variance criterion for separation between character sectioning candidate positions in a line image. The first method is applied to the estimation of the character pitch, i.e., estimating the statistically best character pitch. It also extracts the parameters representing the placement properties for a series of characters. The second method is used to determine in a stable way a series of character sectioning positions. In the experiment, the method is applied to English language mail addresses, containing fixed and unspecified character pitches as well as contact between adjacent characters. A 99.2% correct segmentation rate was obtained for characters and 98.0% was obtained for words, indicating the effectiveness of the method.

Recognition By Two Stage Discriminant Analysis

Two stage discriminant analysis has been proposed for multi class recognition. In the second stage, multiple discriminant analysis is applied to the identification for each set of classes, which are not distinctly classified in the first stage. The proposed method is applied to character recognition for the method estimation. The recognition rate was 99.3% for 91 categories of alphanumerics and special symbols. The recognition speed was 20 milliseconds per character, when this analysis program was executed on image pipelined processors. It has been shown that this method is further applicable to character sequence recognition without the need for a character isolation process.