Time filter

Source Type

Brodic D.,University of Belgrade | Milivojevic Z.N.,Technical College Nis | Maluckov C.A.,University of Belgrade
2015 38th International Conference on Telecommunications and Signal Processing, TSP 2015 | Year: 2015

The paper proposed an algorithm for the identification of the script by adjacent local binary patterns (ALBP). In the first phase, each letter in the text is modeled with the so-called script type, which is based on its status in the baseline area. Then, the feature extraction is made with the adjacent local binary pattern (ALBP). According to ALBP, the distinctive features of the script are set and stored for further analysis. Because of the difference in script characteristics, the analysis shows significant diversity between different scripts. Hence, it represents the key point for decision-making process of script identification. The proposed method is tested on the example of old Slavic printed documents, which contain Latin and Glagolitic script. The results of experiments are encouraging. © 2015 IEEE.


Brodic D.,University of Belgrade | Milivojevic Z.N.,Technical College Nis
International Journal of Reasoning-based Intelligent Systems | Year: 2013

Several approaches have been taken for document text image skew detection. Their assignment was in the domain of efficiency, accuracy and robustness. This paper introduces the method for text skew detection based on the log-polar transformation. The original image is transformed in log-polar domain as well as the control ellipse. Their cross-correlation established the cost function. The extraction of the cost function maximum represents the text skew value in the region. The method is characterised by the accuracy and computational time inexpensiveness. Copyright © 2013 Inderscience Enterprises Ltd.


Brodic D.,University of Belgrade | Milivojevic Z.N.,Technical College Nis | Milivojevic D.R.,Serbian Mining and Metallurgy Institute
Elektronika ir Elektrotechnika | Year: 2012

The paper presents the approach to the algorithm for text line segmentation based on the anisotropic Gaussian kernel. As a result of this algorithm the growing region around text is exploited. Furthermore, anisotropic Gaussian kernel is rotated to improve text line segmentation process. Text objects orientation is evaluated by binary moments. For test purposes algorithm is evaluated under different text samples. From the obtained results comparative analysis between algorithm with anisotropic and oriented Gaussian kernel is made. At the end, benefits of the extended approach are revealed.


Brodic D.,University of Belgrade | Milivojevic Z.N.,Technical college Nis
Radioengineering | Year: 2012

Binary moments represent one of the methods for the text skew estimation in binary images. It has been used widely for the skew identification of the printed text. However, the handwritten text consists of text objects, which are characterized with different skews. Hence, the method should be adapted for the hand written text. This is achieved with the image splitting into separate text objects made by the bounding boxes. Obtained text objects represent the isolated binary objects. The application of the moment-based method to each binary object evaluates their local text skews. Due to the accuracy, estimated skew data can be used as an input to the algorithms for the text line segmentation.


Brodic D.,University of Belgrade | Milivojevic Z.,Technical College Nis
10th Symposium on Neural Network Applications in Electrical Engineering, NEUREL-2010 - Proceedings | Year: 2010

This paper proposes a new approach to water flow algorithm for the text line segmentation. Original method assumes hypothetical water flows under few specified angles to the document image frame from left to right and vice versa. As a result, unwetted image frames are extracted. These areas are of major importance for text line segmentation. Method modifications mean extension values of water flow angle and unwetted image frames function enlargement. Results are encouraging due to text line segmentation improvement which is the most challenging process stage in document image processing. © 2010 IEEE.


Brodic D.,University of Belgrade | Milivojevic Z.N.,Technical College Nis
Elektronika ir Elektrotechnika | Year: 2013

The paper proposed the method for text skew detection based on log-polar transformation. The original image is transformed in the log-polar domain as well as the control ellipse. Theirs cross-correlation established the cost function. The extraction of the cost function maximums gives the text skew value in the left and right region from the centre point of transformation. The method is suitable for the printed text. It is characterized by the accuracy and computational time inexpensiveness.


Brodic D.,University of Belgrade | Milivojevic D.R.,Serbian Mining and Metallurgy Institute | Milivojevic Z.N.,Technical College Nis
Sensors | Year: 2011

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. © 2011 by the authors; licensee MDPI, Basel, Switzerland.


Brodic D.,University of Belgrade | Milivojevic Z.,Technical College Nis
Radioengineering | Year: 2010

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.


Brodic D.,University of Belgrade | Milivojevic Z.,Technical College Nis
Journal of Universal Computer Science | Year: 2011

This paper proposes a new approach to water flow algorithm for the text line segmentation. Original method assumes hypothetical water flows under a few specified angles to the document image frame from left to right and vice versa. As a result, unwetted image frames are extracted. These areas are of major importance for text line segmentation. Method modifications mean extension values of water flow angle and unwetted image frames function enlargement. Results are encouraging due to text line segmentation improvement which is the most challenging process stage in document image processing. © J.UCS.


Brodic D.,University of Belgrade | Milivojevic D.R.,Serbian Mining and Metallurgy Institute | Milivojevic Z.,Technical College Nis
Sensors | Year: 2010

Text line segmentation is an essential stage in off-line optical character recognition (OCR) systems. It is a key because inaccurately segmented text lines will lead to OCR failure. Text line segmentation of handwritten documents is a complex and diverse problem, complicated by the nature of handwriting. Hence, text line segmentation is a leading challenge in handwritten document image processing. Due to inconsistencies in measurement and evaluation of text segmentation algorithm quality, some basic set of measurement methods is required. Currently, there is no commonly accepted one and all algorithm evaluation is custom oriented. In this paper, a basic test framework for the evaluation of text feature extraction algorithms is proposed. This test framework consists of a few experiments primarily linked to text line segmentation, skew rate and reference text line evaluation. Although they are mutually independent, the results obtained are strongly cross linked. In the end, its suitability for different types of letters and languages as well as its adaptability are its main advantages. Thus, the paper presents an efficient evaluation method for text analysis algorithms. © 2010 by the authors.

Loading Technical college Nis collaborators
Loading Technical college Nis collaborators