reported here should be useful for designers of practical systems for these two important commercial applications. For the OCR problem, the Karhunen-Lo`eve (K-L) transform of the images is used to generate the input feature set. Similarly for the fingerprint problem, the K-L transform of the ridge

This paper shows a novel approach to binarization techniques. It presents a way to obtain an optimum threshold using a semantic description of the histogram and a neural network. The intended applications of this technique are high precision OCR algorithms over a limited number of document types

the text. Third, the material to be read from the form has specific, known content, which restricts the lexicon of expected answers. The success or failure of form-based OCR is strongly influenced by the degree to which the application adheres to these constraints. ood form design is essential

scanning or after binarization of scanned document images. White Gaussian noise corrupts the document images during transmission. The presence of either type of noise or a combination of them can severely degrade the performance of any OCR system. In the proposed denoising scheme, the curvelet transform

This paper introduces a learning algorithm for a neural structure, Directed Acyclic Graphs (DAGs) that is structurally based, i.e. reduction and manipulation of internal structure are directly linked to learning. This paper extends the concepts in [1] for template matching to a neural structure with capabilities for generalization. DAG-Learning is derived from concepts in Finite State Transducers, Hidden Markov Models, and Dynamic Time Warping to form an algorithmic framework within which many adaptive signal techniques such as Vector Quantization, K-Means, Approximation Networks, etc., may be extended to temporal recognition. The paper provides a concept of path-based learning to allow comparison among Hidden Markov Models (HMMs), Finite State Transducers (FSTs) and DAG-Learning. The paper also outlines the DAG-Learning process and provides results from the DAG-Learning algorithm over test set of isolated cursive handwriting characters. 1. INTRODUCTION The workhorse for temporal rec...

Lighting, camera resolution and focus, skew (shear), and processing power all contribute to the difficulties in developing effective OCR applications using mobile phones. We propose a novel algorithm using PCA, divergence, and a global neural network to develop an OCR package that levers user

Abstract — Digitization of paper-bound documents is one of the foremost commercial interests worldwide. First step in all such applications is transforming a paper bound document into an electronic document by scanning, subsequently applying to the image OCR to generate textual information from

for many forms of automated data processing and has wide application. A great deal of effort has been devoted to correcting errors which invariably result from commercially available OCR devices. Besides error patterns like substitution, transposition, insertion and deletion, emphasis is given on modifiers

In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of true text through its transformation into the noisy output of an OCR system. The model is designed

Optical Character Recognition (OCR) is a critical part of many text-based applications. Although some commercial systems use the output from OCR devices to index documents without editing, there is very little quantitative data on the impact of OCR errors on the accuracy of a text retrieval system