|
Development
of an Intelligent System for Extraction and Recognition of
Handwritten Characters
-- Rupsa
Chakraborty and Jaya Sil
To
date, many researchers have proposed various methods to recognize
handwritten characters, which in one way or the other use
image segmentation techniques. In this paper, image segmentation
has been avoided successfully to encode the characters in
developing an automated unconstrained handwritten character
recognition system. In the offline mode, several training
images corresponding to each known handwritten character are
fused to generate patterns for each of them. The patterns
are stored in 10×10 matrices, irrespective of the image
sizes, thus saving storage space significantly. In real time,
characters are extracted by sampling the handwritten scripts
at different intervals determined heuristically. Extracted
characters are matched with the stored patterns for recognition.
The characters which do not match are classified as disjoint
components and processed further for recognition. In order
to develop a robust system, the characters are represented
as fuzzy sets, and a fuzzy confidence value for each of them
is computed for recognition. This method is applicable for
verification of the recognized characters too. Based on the
system feedback, more training images can be fused at any
point of processing, which improves recognition rate. The
system is tested with a large number of handwritten scripts,
independent of the writing style to demonstrate its effectiveness.
© 2007 IUP . All Rights Reserved.
Parallel
Crosstalk Minimization Algorithms for Two-Layer Channel Routing
-- Achira Pal, Rajat K Pal and
Alak K Datta
Due
to the advancements in fabrication technology, the devices
and interconnection wires are placed in closer proximity,
and the circuits operate at higher frequencies. This results
in crosstalk between wire segments. Work on routing channels
with reduced crosstalk is a very important area of current
research (Gao and Liu, 1993; and Pal, 2000). We know that
the crosstalk minimization problem in the reserved two-layer
Manhattan routing model is NP-complete, even for the channels
without any vertical constraints (Pal et al., 2007).
Since minimizing crosstalk is NP-complete, several polynomial
time heuristic algorithms for reducing crosstalk have been
developed (Pal et al., 2002, 2004 and 2006; and Singha
et al., 2002). All the ideas that are introduced as
heuristics are basically sequential in nature. This paper,
develops two efficient parallel heuristic algorithms for computing
reduced crosstalk routing solutions. The heuristics proposed
in this paper are much better in computational complexity
than the existing sequential versions of the algorithms developed
previously (Pal et al., 2002 and 2006; and Singha et
al., 2002).
© 2007 IUP . All Rights Reserved.
The
Business Rules Diagram
-- Donald
C McDermid
This
paper reports the action research conducted into the issues
of introducing structure into informal information requirements
for deciding which constructs are appropriate for describing
information requirements. The outcome of this research was
the development of a Business Rules Diagram (BRD) and a technique
for assisting its construction. A critical epistemological
gap is asserted to exist between those who capture information
requirements in human activity systems (typically, informally)
and those who specify and deliver information systems. The
paper demonstrates how modelling business rules can bridge
that gap. A definition of a business rule and also a complete
description of the notation of the BRD and the steps for its
creation are provided.
© 2007 IUP . All Rights Reserved.
Research
Note
Fuzzy-Neuro
Driven Computer Cars in Racing Games
--
John
R Rankin and Chun Kwok Tim Wong
Racing
games have always been one of the most popular game genres
among all types of game consoles. Players of racing games
have to control a racing car and drive it to the goal as quickly
as possible. A lot of skill is required to manoeuvre the car,
which involves movements such as turning, accelerating, decelerating
and overtaking.
© 2007 IUP . All Rights Reserved.
Projective
Geometry Tool for Canonical Cover
--
K Venkateswara Rao, C R Rao and V Kamaskshi Prasad
It
is desirable to impose proper constraints while designing
a database, in order to provide efficient information storage
and retrieval methods. Identifying and applying the key dependencies
on the database is one of the essential features of database
design (Date, 1996; and Silbreschatz et al., 1997).
While designing a database, there is a possibility that certain
dependencies are overlooked. Further, there may be a number
of key dependencies, which may not be known at the time of
database design, and that affects the efficiency of a Database
Management System (DBMS). Hence, it is a general practice
to consider expert views while identifying functional dependencies.
Extraction of functional dependencies is the fundamental activity
in the database design recovery process, which is a part of
an overall system reverse engineering effort.
© 2007 IUP . All Rights Reserved.
A
Graph-based Algorithm for Determining the
Lossless-Join Property of Schema Decompositions
-- P
S Gill and L M Patnaik
The
process of normalizing a global schema involves its decomposition
into sub-schemas, on the basis of data dependencies existing
in the global schema. While decomposing a schema into sub-schemas,
it is to be ensured that the decomposition is lossless-join
decomposition (or non-loss decomposition). Presently, there
exists an algorithm proposed by Aho, Beeri and Ullman (1979),
popularly known as ABU's algorithm, that is used to determine
whether a given decomposition is a non-loss decomposition
or not. This paper proposes a graph-based algorithm to perform
the same task.
© 2007 IUP . All Rights Reserved.
|
