OALib Journal期刊

ISSN: 2333-9721



匹配条件: “BRODIC” ,找到相关结果约6条。
Optimization of the Gaussian Kernel Extended by Binary Morphology for Text Line Segmentation
D. Brodic,Z. Milivojevic
Radioengineering , 2010,
Abstract: In this paper, an approach for text line segmentation by algorithm with the implementation of the Gaussian kernel is presented. As a result of algorithm, the growing area around text is exploited for text line segmentation. To improve text line segmentation process, isotropic Gaussian kernel is extended by dilatation. Furthermore, algorithms with isotropic and extended Gaussian kernels are examined and evaluated under different text samples. Results are given and comparative analysis is made for these algorithms. From the obtained results, optimization of the parameters defining extended Gaussian kernel dimension is proposed. The presented algorithm with the extended Gaussian kernel showed robustness for different types of text samples.
Classification of the Extremely Low Frequency Magnetic Field Radiation Measurement from the Laptop Computers
Darko Brodic,Alessia Amelio
Computer Science , 2015, DOI: 10.1515/msr-2015-0028
Abstract: The paper considers the level of the extremely low-frequency magnetic field, which is produced by laptop computers. The magnetic field, which is characterized by extremely low frequencies up to 300 Hz is measured due to its hazardous effects to the laptop user's health. The experiment consists of testing 13 different laptop computers in normal operation conditions. The measuring of the magnetic field is performed in the adjacent neighborhood of the laptop computers. The measured data are presented and then classified. The classification is performed by the K-Medians method in order to determine the critical positions of the laptop. At the end, the measured magnetic field values are compared with the critical values suggested by different safety standards. It is shown that some of the laptop computers emit a very strong magnetic field. Hence, they must be used with extreme caution.
The Effects of the Acute Hypoxia to the Fundamental Frequency of the Speech Signal
Advances in Electrical and Computer Engineering , 2012, DOI: 10.4316/aece.2012.02010
Abstract: When people that live at the small altitudes (up to 400 m above the sea level) climb on the mountain, they are exposed to the effects of an acute hypoxia. As a consequence, theirs oxygen concentration decreases in the tissue. This paper presents the analysis of the acute hypoxia effects to the speech signal at the altitudes up to 2600 m above the sea level. For the experiment, the articulation of vowels (A, E, I, O, U) from the test group of persons was recorded at different altitudes, which creates the speech signal database. The speech signal from database is processed by the original algorithm. As the results, the fundamental frequency and the energy of dissonant intervals of speech signal are obtained. Furthermore, the acute hypoxia effect to the energy distribution in the dissonant intervals of the speech signal is analyzed. At the end, the comparative analysis of the acute hypoxia effects shows that the level of the hypoxia can be determined by the change of the fundamental frequency and the energy of the dissonant intervals of speech signal. Hence, it is possible to bring conclusions about the degree of hypoxia, which in many situations can be of importance for avoiding catastrophic consequences.
Analysis of the South Slavic Scripts by Run-Length Features of the Image Texture
Darko Brodic,Zoran N. Milivojevic,Alessia Amelio
Computer Science , 2015, DOI: 10.5755/j01.eee.21.4.12785
Abstract: The paper proposes an algorithm for the script recognition based on the texture characteristics. The image texture is achieved by coding each letter with the equivalent script type (number code) according to its position in the text line. Each code is transformed into equivalent gray level pixel creating an 1-D image. Then, the image texture is subjected to the run-length analysis. This analysis extracts the run-length features, which are classified to make a distinction between the scripts under consideration. In the experiment, a custom oriented database is subject to the proposed algorithm. The database consists of some text documents written in Cyrillic, Latin and Glagolitic scripts. Furthermore, it is divided into training and test parts. The results of the experiment show that 3 out of 5 run-length features can be used for effective differentiation between the analyzed South Slavic scripts.
An Approach to the Analysis of the South Slavic Medieval Labels Using Image Texture
Darko Brodic,Alessia Amelio,Zoran N. Milivojevic
Computer Science , 2015,
Abstract: The paper presents a new script classification method for the discrimination of the South Slavic medieval labels. It consists in the textural analysis of the script types. In the first step, each letter is coded by the equivalent script type, which is defined by its typographical features. Obtained coded text is subjected to the run-length statistical analysis and to the adjacent local binary pattern analysis in order to extract the features. The result shows a diversity between the extracted features of the scripts, which makes the feature classification more effective. It is the basis for the classification process of the script identification by using an extension of a state-of-the-art approach for document clustering. The proposed method is evaluated on an example of hand-engraved in stone and hand-printed in paper labels in old Cyrillic, angular and round Glagolitic. Experiments demonstrate very positive results, which prove the effectiveness of the proposed method.
An Approach to a Comprehensive Test Framework for Analysis and Evaluation of Text Line Segmentation Algorithms
Darko Brodic,Dragan R. Milivojevic,Zoran N. Milivojevic
Sensors , 2011, DOI: 10.3390/s110908782
Abstract: The paper introduces a testing framework for the evaluation and validation of text line segmentation algorithms. Text line segmentation represents the key action for correct optical character recognition. Many of the tests for the evaluation of text line segmentation algorithms deal with text databases as reference templates. Because of the mismatch, the reliable testing framework is required. Hence, a new approach to a comprehensive experimental framework for the evaluation of text line segmentation algorithms is proposed. It consists of synthetic multi-like text samples and real handwritten text as well. Although the tests are mutually independent, the results are cross-linked. The proposed method can be used for different types of scripts and languages. Furthermore, two different procedures for the evaluation of algorithm efficiency based on the obtained error type classification are proposed. The first is based on the segmentation line error description, while the second one incorporates well-known signal detection theory. Each of them has different capabilities and convenience, but they can be used as supplements to make the evaluation process efficient. Overall the proposed procedure based on the segmentation line error description has some advantages, characterized by five measures that describe measurement procedures.

Copyright © 2008-2017 Open Access Library. All rights reserved.