<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
<channel>
<title>Volumen 05 | Número 03</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/389</link>
<description/>
<pubDate>Wed, 18 Nov 2026 19:06:44 GMT</pubDate>
<dc:date>2026-11-18T19:06:44Z</dc:date>
<item>
<title>Manuscript document digitalization and recognition: a first approach</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/5521</link>
<description>Articulo
Journal of Computer Science &amp; Technology; vol. 5, no. 3
The handwritten manuscript recognizing process belongs to a set of initiatives which lean to the preservation of cultural patrimony gathered in libraries and archives, where there exist a great wealth in documents and even handwritten cards that accompany incunabula books. This work is the starting point of a research and development project oriented to digitalization and recognition of manuscript materials. The paper presented here discuss different algorithms used in the first stage dedicated to "image noise-cleaning" in order to improve it before the character recognition process begins. In order to make the handwritten-text recognition and image digitalization process efficient, it must be preceded by a preprocessing stage of the image to be treated, which includes thresholding, noise cleaning, thinning, base-line alignment and image segmentation, among others. Each of these steps will allow us to reduce the injurious variability when recognizing manuscripts (noise, random gray levels, slanted characters, ink level in different zones), and so increasing the probability of obtaining a suitable text recognition. In this paper, two image thinning methods are considered, and implemented. Finally, an evaluation is carried out obtaining many conclusions related to efficiency, speed and requirements, as well as ideas for future implementations.
</description>
<pubDate>Sat, 01 Oct 2005 00:00:00 GMT</pubDate>
<guid isPermaLink="false">http://sedici.unlp.edu.ar:80/handle/10915/5521</guid>
<dc:date>2005-10-01T00:00:00Z</dc:date>
<dc:description>The handwritten manuscript recognizing process belongs to a set of initiatives which lean to the preservation of cultural patrimony gathered in libraries and archives, where there exist a great wealth in documents and even handwritten cards that accompany incunabula books. This work is the starting point of a research and development project oriented to digitalization and recognition of manuscript materials. The paper presented here discuss different algorithms used in the first stage dedicated to "image noise-cleaning" in order to improve it before the character recognition process begins. In order to make the handwritten-text recognition and image digitalization process efficient, it must be preceded by a preprocessing stage of the image to be treated, which includes thresholding, noise cleaning, thinning, base-line alignment and image segmentation, among others. Each of these steps will allow us to reduce the injurious variability when recognizing manuscripts (noise, random gray levels, slanted characters, ink level in different zones), and so increasing the probability of obtaining a suitable text recognition. In this paper, two image thinning methods are considered, and implemented. Finally, an evaluation is carried out obtaining many conclusions related to efficiency, speed and requirements, as well as ideas for future implementations.</dc:description>
</item>
<item>
<title>Classification of color textures with random field models and neural networks</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/9587</link>
<description>Articulo
Journal of Computer Science &amp; Technology; vol. 5, no. 3
A number of texture classification approaches have been developed in the past but most of these studies target graylevel textures. In this work, novel results are presented on Neural Network based classification of color textures in a very large heterogeneous database. Several different Multispectral Random Field models are used to characterize the textures. The classifying features are based on the estimated parameters of these model and functions defined on them. The approach is tested on a database of 73 different color textures classes. The advantage of utilizing color information is demonstrated by converting color textures to gray-level ones and classifying them using Grey Level Co-Occurrence Matrix (GLCM) based features.
</description>
<pubDate>Sat, 01 Oct 2005 00:00:00 GMT</pubDate>
<guid isPermaLink="false">http://sedici.unlp.edu.ar:80/handle/10915/9587</guid>
<dc:date>2005-10-01T00:00:00Z</dc:date>
<dc:description>A number of texture classification approaches have been developed in the past but most of these studies target graylevel textures. In this work, novel results are presented on Neural Network based classification of color textures in a very large heterogeneous database. Several different Multispectral Random Field models are used to characterize the textures. The classifying features are based on the estimated parameters of these model and functions defined on them. The approach is tested on a database of 73 different color textures classes. The advantage of utilizing color information is demonstrated by converting color textures to gray-level ones and classifying them using Grey Level Co-Occurrence Matrix (GLCM) based features.</dc:description>
</item>
<item>
<title>A making-decision system for an urban transportation network</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/9586</link>
<description>Articulo
Journal of Computer Science &amp; Technology; vol. 5, no. 3
This paper deals with the real time regulation of traffic within a disturbed transportation system. We show the necessity of a decision support system that detects, analyzes and resolves the unpredicted disturbances. Due to the disturbed aspect of transportation system, we present a multi-agent approach for the regulation process. This approach includes an anytime algorithm, which permits to access to solutions in real time. The quality of the results increases with allocated time. Our system is able to foresee all behaviors according to the environment with which it interacts. These aims offer real guarantees with respect to the temporal deadlines. The main objective is not to search an optimal solution for a disturbance, but to define a set of possible solutions.
</description>
<pubDate>Sat, 01 Oct 2005 00:00:00 GMT</pubDate>
<guid isPermaLink="false">http://sedici.unlp.edu.ar:80/handle/10915/9586</guid>
<dc:date>2005-10-01T00:00:00Z</dc:date>
<dc:description>This paper deals with the real time regulation of traffic within a disturbed transportation system. We show the necessity of a decision support system that detects, analyzes and resolves the unpredicted disturbances. Due to the disturbed aspect of transportation system, we present a multi-agent approach for the regulation process. This approach includes an anytime algorithm, which permits to access to solutions in real time. The quality of the results increases with allocated time. Our system is able to foresee all behaviors according to the environment with which it interacts. These aims offer real guarantees with respect to the temporal deadlines. The main objective is not to search an optimal solution for a disturbance, but to define a set of possible solutions.</dc:description>
</item>
<item>
<title>Evolutionary multiobjetive optimization in non-stationary environments</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/9585</link>
<description>Articulo
Journal of Computer Science &amp; Technology; vol. 5, no. 3
This paper proposes an approach, called Multiobjective Algorithm for Dynamic Environments (MADE), which extendes Fonseca and Fleming's MOGA (with an external archive) so that it can deal with dynamic environments. MADE includes two techniques to maintain diversity and also uses specialized functions that implements the dynamism required. In order to validate MADE, we defined a dynamic version of a static test problem (with 3 objectives) previously proposed in the specialized literature. The preliminary results obtained indicate that the proposed approach provides an acceptable response to the type of changes studied.
</description>
<pubDate>Sat, 01 Oct 2005 00:00:00 GMT</pubDate>
<guid isPermaLink="false">http://sedici.unlp.edu.ar:80/handle/10915/9585</guid>
<dc:date>2005-10-01T00:00:00Z</dc:date>
<dc:description>This paper proposes an approach, called Multiobjective Algorithm for Dynamic Environments (MADE), which extendes Fonseca and Fleming's MOGA (with an external archive) so that it can deal with dynamic environments. MADE includes two techniques to maintain diversity and also uses specialized functions that implements the dynamism required. In order to validate MADE, we defined a dynamic version of a static test problem (with 3 objectives) previously proposed in the specialized literature. The preliminary results obtained indicate that the proposed approach provides an acceptable response to the type of changes studied.</dc:description>
</item>
<item>
<title>A robust agorithm for eye detection on gray intensity face without spectacles</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/9584</link>
<description>Articulo
Journal of Computer Science &amp; Technology; vol. 5, no. 3
This paper presents a robust eye detection algorithm for gray intensity images. The idea of our method is to combine the respective advantages of two existing techniques, feature based method and template based method, and to overcome their shortcomings. Firstly, after the location of face region is detected, a feature based method will be used to detect two rough regions of both eyes on the face. Then an accurate detection of iris centers will be continued by applying a template based method in these two rough regions. Results of experiments to the faces without spectacles show that the proposed approach is not only robust but also quite efficient.
</description>
<pubDate>Sat, 01 Oct 2005 00:00:00 GMT</pubDate>
<guid isPermaLink="false">http://sedici.unlp.edu.ar:80/handle/10915/9584</guid>
<dc:date>2005-10-01T00:00:00Z</dc:date>
<dc:description>This paper presents a robust eye detection algorithm for gray intensity images. The idea of our method is to combine the respective advantages of two existing techniques, feature based method and template based method, and to overcome their shortcomings. Firstly, after the location of face region is detected, a feature based method will be used to detect two rough regions of both eyes on the face. Then an accurate detection of iris centers will be continued by applying a template based method in these two rough regions. Results of experiments to the faces without spectacles show that the proposed approach is not only robust but also quite efficient.</dc:description>
</item>
<item>
<title>A Weighted K-means Algorithm applied to Brain Tissue Classification</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/9583</link>
<description>Articulo
Journal of Computer Science &amp; Technology; vol. 5, no. 3
Tissue classification in Magnetic Resonance (MR) brain images is an important issue in the analysis of several brain dementias. This paper presents a modification of the classical K-means algorithm taking into account the number of times specific features appear in an image, employing, for that purpose, a weighted mean to calculate the centroid of every cluster. Pattern Recognition techniques allow grouping pixels based on features similarity. In this paper, multispectral gray-level intensity MR brain images are used. T1, T2 and PD-weighted images provide different and complementary information about the tissues. Segmentation is performed in order to classify each pixel of the resulting image according to four possible classes: cerebro-spinal fluid (CSF), white matter (WM), gray matter (GM) and background. T1, T2 and PD-weighted images are used as patterns. The proposed algorithm weighs the number of pixels corresponding to each set of gray levels in the feature vector. As a consequence, an automatic segmentation of the brain tissue is obtained. The algorithm provides faster results if compared with the traditional K-means, thereby retrieving complementary information from the images.
</description>
<pubDate>Sat, 01 Oct 2005 00:00:00 GMT</pubDate>
<guid isPermaLink="false">http://sedici.unlp.edu.ar:80/handle/10915/9583</guid>
<dc:date>2005-10-01T00:00:00Z</dc:date>
<dc:description>Tissue classification in Magnetic Resonance (MR) brain images is an important issue in the analysis of several brain dementias. This paper presents a modification of the classical K-means algorithm taking into account the number of times specific features appear in an image, employing, for that purpose, a weighted mean to calculate the centroid of every cluster. Pattern Recognition techniques allow grouping pixels based on features similarity. In this paper, multispectral gray-level intensity MR brain images are used. T1, T2 and PD-weighted images provide different and complementary information about the tissues. Segmentation is performed in order to classify each pixel of the resulting image according to four possible classes: cerebro-spinal fluid (CSF), white matter (WM), gray matter (GM) and background. T1, T2 and PD-weighted images are used as patterns. The proposed algorithm weighs the number of pixels corresponding to each set of gray levels in the feature vector. As a consequence, an automatic segmentation of the brain tissue is obtained. The algorithm provides faster results if compared with the traditional K-means, thereby retrieving complementary information from the images.</dc:description>
</item>
<item>
<title>Development and tuning framework of master/worker applications</title>
<link>http://sedici.unlp.edu.ar:80/handle/10915/9582</link>
<description>Articulo
Journal of Computer Science &amp; Technology; vol. 5, no. 3
Parallel/distributed programming is a complex task that requires a high degree of expertise to fulfill the expectations of high performance computation. The Master/Worker paradigm is one of the most commonly used because it is easy to understand and there is a wide range of applications that match this paradigm. However, there are certain features, such as data distribution and the number of workers that must be tuned properly to obtain adequate performance. In most cases such features cannot be tuned statically since they depend on the particular conditions of each execution. In this paper, we show a dynamic tuning environment that is based on a theoretical model of Master/Worker behavior and allows for the adaptation of such applications to the dynamic conditions of execution. The environment includes a pattern based application development framework that allows the user to concentrate on the design phase and makes it easier to overcome performance bottlenecks.
</description>
<pubDate>Sat, 01 Oct 2005 00:00:00 GMT</pubDate>
<guid isPermaLink="false">http://sedici.unlp.edu.ar:80/handle/10915/9582</guid>
<dc:date>2005-10-01T00:00:00Z</dc:date>
<dc:description>Parallel/distributed programming is a complex task that requires a high degree of expertise to fulfill the expectations of high performance computation. The Master/Worker paradigm is one of the most commonly used because it is easy to understand and there is a wide range of applications that match this paradigm. However, there are certain features, such as data distribution and the number of workers that must be tuned properly to obtain adequate performance. In most cases such features cannot be tuned statically since they depend on the particular conditions of each execution. In this paper, we show a dynamic tuning environment that is based on a theoretical model of Master/Worker behavior and allows for the adaptation of such applications to the dynamic conditions of execution. The environment includes a pattern based application development framework that allows the user to concentrate on the design phase and makes it easier to overcome performance bottlenecks.</dc:description>
</item>
</channel>
</rss>
