We consider the problem of assessing the reliability of a character recognition system, and in particular, the amount of data required to numerically estimate this reliability.

1 Now, he works for Hitachi in Japan Abstract Structural matching and feature matching are two major streams in handwritten Chinese character recognition. The former is better in absorbing writing variation since it utilizes rich structural information from strokes directly. However, it is worse than the latter in handling noisy images, because of the difficulty in stroke extraction. For the ul...

Automatic reading of number plate in vehicles is a character recognition system, which detects the characters from the segmented number plate of the vehicle image. The work presented in this paper is to segment the characters initially from the number plate followed by recognition of the segmented characters. The skew corrected and noise free number plate image is initially segmented into its c...

A method for the fronto-parallel recovery of paragraphs of text under full perspective transformation is presented. The horizontal vanishing point of the text plane is found using an extension of 2D projection profiles. This allows the accurate segmentation of the lines of text. Analysis of the lines will then reveal the style of justification of the paragraph, and provide an estimate of the ve...

A novel confidence-based parallel multiple expert decision combination framework is introduced. The traditional approaches to parallel multiple source decision fusion either take no account of the confidence of each decision by each participating expert in the combined framework or only exploit the confidences associated with each decision. But it is entirely possible to incorporate more additi...

Analytic shrinkage is a statistical technique that offers a fast alternative to crossvalidation for the regularization of covariance matrices and has appealing consistency properties. We show that the proof of consistency requires bounds on the growth rates of eigenvalues and their dispersion, which are often violated in data. We prove consistency under assumptions which do not restrict the cov...

Optical character recognition (OCR) is a very popular research area since 1950's. Many people has done a lot of work on various scripts. Line segmentation is a very important step in OCR as the accuracy of the recognition algorithm highly depends on the correct line segmentation. Incorrect line segmentation not only decreases the accuracy but also may lead to some other errors. The objective of...

The National Library of Medicine has developed a system for the automatic extraction of data from scanned journal articles to populate the MEDLINE database. Although the 5-engine OCR system used in this process exhibits good performance overall, it does make errors in character recognition that must be corrected in order for the process to achieve the requisite accuracy. The correction process ...

Most OCR (Optical Character Recognition) systems developed to recognize texts embedded in multimedia documents segment the text into characters before recognizing them. In this paper, we propose a novel approach able to avoid any explicit character segmentation. Using a multi-scale scanning scheme, texts extracted from videos are first represented by sequences of learnt features. Obtained repre...

In this paper we propose an approach for offline recognition of Tamil characters using their structural features. Structural features are the features that are physically a part of the structure of the character, such as straight lines, arcs, circles, intersections etc. The features used for recognition are the positions of vertical lines, horizontal lines and branching in a character. Some oth...