Two word slant correction methods are evaluated in this work using handwritten numeral strings. A method originally proposed to word slant correction is adapted in order to improve the results for handwritten numeral strings. The original and modified methods are evaluated by means of some interesting analyses on the NIST SD19 database. In these analyses the difference, in terms of slant estima...

Variations in inter-line gaps and skewed or curled text-lines are some of the challenging issues in segmentation of handwritten text-lines. Moreover, overlapping and touching text-lines that frequently appear in unconstrained handwritten text documents significantly increase segmentation complexities. In this paper, we propose a novel approach for unconstrained handwritten text-line segmentatio...

In this paper we address the issue of recognizing Farsi handwritten words. Two types of gradient features are extracted from a sliding vertical stripe which sweeps across a word image. These are directional and intensity gradient features. The feature vector extracted from each stripe is then coded using the Self Organizing Map (SOM). In this method each word is modeled using the discrete Hidde...

A dramatic perceptual asymmetry occurs when handwritten words are rotated 90 ° in either direction. Those rotated in a direction consistent with their natural tilt (typically clockwise) become much more difficult to recognize, relative to those rotated in the opposite direction. In Experiment 1, we compared computer-printed and handwritten words, all equated for degrees of leftward and rightwar...

In this paper, we present the creation of the first comprehensive database for research and development on handwritten recognition of Dari language. This new handwritten database consists of many aspects of Dari scripts such as: handwritten isolated characters, isolated digits, numeral strings of various lengths, many words/terms, dates, and some special symbols. For each handwritten image in t...

In data grid, using reservation is accepted to provide scheduling and service quality. Users need to have an access to the stored data in geographical environment, which can be solved by using replication, and an action taken to reach certainty. As a result, users are directed toward the nearest version to access information. The most important point is to know in which sites and distributed sy...

In this paper we report the use of discriminative training and other techniques to improve performance in a HMMbased isolated handwritten character recognition system. The discriminative training is Maximum Mutual Information (MMI) training; we also improve results by using composite images which are the concatenation of the raw images, rotated and polar transformed versions of them; and we des...

We report on the implementation and computational testing of several versions of a set covering algorithm, based on the family of cutting planes from conditional bounds discussed in the companion paper [2]. The algorithm uses a set of heuristics to find prime covers, another set of heuristics to find feasible solutions to the dual linear program which are needed to generate cuts, and subgradien...

Separating handwritten and typewritten text within unconstrained paper documents can provide more accurate and efficient OCR results. This paper presents a technique developed that can isolate both the typewritten and handwritten portions of a document image. The classification between handwritten and typewritten text occurs at both the character and the word level. Characters are grouped into ...