In this paper, a new algorithm to construct a multitemplate dictionary for character recognition is presented. It is a repetitive process of partitioning and estimating the distribution by observing both within-class distribution and between-class information. The effectiveness of the algorithm is shown by experimental results.

Expertise in Chinese character recognition is marked by analytic/reduced holistic processing (Hsiao & Cottrell, 2009), which depends mainly on readers’ writing rather than reading experience (Tso, Au, & Hsiao, 2011). Here we examined whether simplified and traditional Chinese readers process characters differently in terms of holistic processing. When processing characters that are distinctive ...

This survey describes the state of art of feature extraction based on allograph in the field of character recognition. It is based on extensive review of the literature on various definitions given by researchers on shape recognition algorithms particularly based on allograph. Keywords— Optical Character Recognition, allograph, feature extraction.

Odia is one of the oldest and popular languages of India, spoken by more than 44 million people, especially in Odisha, India. Some characters in Odia are made up of more than one connected symbols. Compound characters are written by associating modifiers with consonants, resulting in a huge number of possible combinations, running into hundreds of thousands. Therefore, systems developed for rec...

We propose a new statistical method for learning normalized confidence values in multiple classifier systems. Our main idea is to adjust confidence values so that their nominal values equal the information actually conveyed. In order to do so, we assume that information depends on the actual performance of each confidence value on an evaluation set. As information measure, we use Shannon’s well...

Mobile document image acquisition integrates many distortions which must be corrected or detected on the device, before the document becomes unavailable or paying data transmission fees. In this paper, we propose a system to correct perspective and illumination issues, and estimate the sharpness of the image for OCR recognition. The correction step relies on fast and accurate border detection f...

This application note shows how to envision, describe, and realize a design using fuzzy logic. It is not intended to be an introduction to fuzzy logic, but it is basic enough to be understood by designers with a cursory understanding of the subject. For those who seek an introduction to fuzzy logic, the Freescale Fuzzy Logic Educational Kit is an excellent primer. Other sources of information a...

Optical character recognition (OCR) systems for machine-printed documents typically require large numbers of font styles and character models to work well. When given a document printed in an unseen font, the performance of those systems degrade even in the absence of noise. In this paper, we perform OCR in an unsupervised fashion without using any character models by using a cryptogram decodin...

The work presented here involves the design of a Multi Layer Perceptron (MLP) based classifier for recognition of handwritten Bangla alphabet using a 76 element feature set Bangla is the second most popular script and language in the Indian subcontinent and the fifth most popular language in the world. The feature set developed for representing handwritten characters of Bangla alphabet includes...

In this article we describe an optical recognition system for historic lute tablature prints that we have built with the aid of the Gamera toolkit for document analysis and recognition. We give recognition rates for various historic sources and show that our system works quite well on printed tablature sources using movable types. For engraved and manuscript sources, we discuss some principal c...