|
Persian Document Recognition Using Novel Persian Word Indexing Technique and
Fused Shape Matching Method |
|
|
Hamed Habibi Aghdam |
|
Conference : ICDIP , Singapore, Febuary - 2010 |
|
Abstract - There are two main techniques for recognizing Persian
documents. Segmentation technique has been studied completely and several
applicable methods were proposed using this technique. In contrast shape
matching techniques is still active research area and few methods proposed for
this technique. In fact they are complementary techniques which fusion of them
produces a powerful tool for recognizing Persian documents. In this paper we
study the major segmentation methods and analyze their functionality from
different views. Then, we show how shape matching method works and propose a
novel Persian word indexing technique. Finally we describe how these two methods
can be fused and test several aspects of the proposed method. |
|
|
|
|
A Simulated Annealing Approach for Maximizing the Accrued Utility of an
Isochronal Soft Real-Time System |
|
|
Ali Asghar Pourhaji Kazem, Neda Dadashkhani, Mehdi Kargahi, Hamed Habibi Aghdam |
|
Conference : ICECS , Dubai , UAE , December - 2009 |
|
|
|
|
Novel Framework for Selecting the Optimal Feature Vector from Large Feature
Spaces |
|
|
Hamed Habibi Aghdam - Saeid Payvar |
|
Journal : Accepted in Journal of Communication and Computer, USA,
August-2009 |
|
|
|
|
Novel Framework for Selecting the Optimal Feature Vector from Large Feature
Spaces |
|
|
Hamed Habibi Aghdam - Saeid Payvar |
|
Abstract - There are several feature extracting techniques which can
produce a large feature space for a given image. It is clear that only small
numbers of these features are appropriate to classify the objects. But selecting
an appropriate feature vector from the large feature space is a hard
optimization problem. In this paper we address this problem using the well known
optimization technique called Simulated Annealing. Also we show that how this
framework can be used to design the optimal 2D rectangular filter banks for
Printed Persian and English numerals classification, Printed English letters
classification, Eye, Lip and Face detection problems. |
|
Conference : ICIAR 2009 - Halifax, Canada, July-2009 |
|
|
|
|
A Novel Corner Detector with Integrated Corner Angle Computation |
|
|
Hamed Habibi Aghdam - Ali Asghar Pourhaji Kazem |
|
Abstract - Corner detection is widely used in image processing and
machine vision. Hence, different corner detectors are proposed. But the
performance of such corner detectors is sensitive to round effect and curve
shape of the edges. In this paper we propose a novel corner detector that either
over come corner detection problems and produces some information about detected
corners that is very useful in segmentation and object recognition. |
|
Conference : IWSSIP 2008 - Bratislava, Slovak Republic, July-2008 |
|
|
|
|
A Modified Simulated Annealing Algorithm for Static Task Scheduling in Grid
Computing |
|
|
Hamed Habibi Aghdam - Ali Asghar Pourhaji Kazem - Amir Masoud Rahmani |
|
Abstract - Grid Computing aims to allow unified access to data, computing
power, sensors and other resources through a single virtual laboratory. The
development or adaptation of applications for Grid environments is being
challenged by the need of scheduling a large number of tasks and resources
efficiently. The general problem of optimally mapping tasks to machines in a
heterogeneous computing suite has been shown to be NP-complete. In this paper we
propose a modified simulated annealing algorithm for scheduling independent
tasks in Grid environment. Experimental results show that our proposed algorithm
improves the performance of static instances compared to the results of other
algorithms reported in the literature. |
|
Conference : ICCSIT 2008 - Singapore, September-2008 |
|
|
|
|
Practical Framework for Extracting Data from Matrix Based Documents |
|
|
Hamed Habibi Aghdam |
|
Abstract - One of the major applications of the image processing is
extracting data from digitally scanned documents. But in some cases such as
matrix based documents, we cannot use any OCR techniques for this purpose. In
this paper we propose a practical framework for developing an autonomous data
extraction and classification system for matrix based documents. Considering
that this is a practical paper, we do not introduce any new methods but
practical results of implemented data extraction system from the special
digitally scanned documents. |
|
Conference : IVCNZ 2008 - New Zealand, November-2008 |
|
|
|