Mustapha Oujaoura | Fst Beni Mellal (original) (raw)
Papers by Mustapha Oujaoura
This paper provides an approach to automatically recognize the Tifinagh characters. The proposed ... more This paper provides an approach to automatically recognize the Tifinagh characters. The proposed recognition system is based on Texture, Walsh transformation and GIST descriptors as feature extraction methods while the Bayesian Networks are used as a classifier. A comparative study between the Texture descriptor, Walsh transformation and GIST descriptor is given. The experimental results are obtained using a character database of isolated Amazigh characters. A recognition rate of 98.18 % is achieved using GIST descriptors.
Journal of Physics: Conference Series, 2021
Accurate monitoring of agricultural lands and crop types is a crucial tool for sustainable food p... more Accurate monitoring of agricultural lands and crop types is a crucial tool for sustainable food production. Therefore, to provide reliable and updated crop maps, the improvement of satellite image classification approaches is essential. In this context, machine learning algorithms present a potential tool for efficient and effective classification of remotely sensed data. The main strengths of machine learning algorithms are the capacity to handle data of high dimensionality, and mapping classes characterized by strong complex dynamics. The main objective of this work was to develop a new synergistic approach for crop discrimination in the semi-arid region of Chichaoua province, located in the Marrakesh-Safi region, Morocco, using high spatio-temporal resolution imagery and a multiple combination of machine learning classifiers. This approach was developed based on 10m spatial resolution open access Sentinel-2 (S2) images and machine learning algorithms. The atmospherically correcte...
Pattern Recognition and Image Analysis, 2016
A large percentage of photos on the Internet cannot be reached by search engines because of the s... more A large percentage of photos on the Internet cannot be reached by search engines because of the semantic gap due to the absence of textual meta data. Despite of decades of research, neither model based approaches can provide quality annotation to images. Many segmentation algorithms use a low level predi cates to control the homogeneity of the regions. So, the resulting regions are not always being semantically compact. The first proposed approach to resolve this problem is to regroup the adjacent region of image. Many features extraction method and classifiers are also used singly, with modest results, for automatic image annotation. The second proposed approach is to select and combine together some efficient descriptors and classifiers. This document provides a hybrid semantic annotation system that combines both approaches in hopes of increasing the accuracy of the resulting annotations. The color histograms, Texture, GIST and invariant moments, used as features extraction methods, are combined together with multi class support vec tor machine, Bayesian networks, Neural networks and nearest neighbor classifiers, in order to annotate the image content with the appropriate keywords. The accuracy of the proposed approach is supported by the good experimental results obtained from two image databases (ETH 80 and coil 100 databases).
Detection recognition and analysis of human faces are some of the most interesting subjects of co... more Detection recognition and analysis of human faces are some of the most interesting subjects of computer vision, especially in a video stream. In the last few years, the algorithms of learning facial features have evolved in many ways, and since the capacity of detecting and reading the human facial features is extremely powerful and is becoming more and more efficient, it will lead us to detect a certain specific data that can be used for security purposes. On the other hand, the appearance of the special bases of command and coordination that enter in the political safe cities projects makes it a huge deal of interest to use these models for empowering those cameras to detect and identify target people. In This article, we propose a real-time intelligent monitoring system that has as objective to detect a specific accuracy of figures of wanted people that had already been studied and learned by a pre-trained model that describe the data in the learning stage through extracting feat...
Abstract—The explosive growth of image data leads to the research and development of image conten... more Abstract—The explosive growth of image data leads to the research and development of image content searching and indexing systems. Image annotation systems aim at annotating automatically animage with some controlled keywords that can be used for indexing and retrieval of images. This paper presents a comparative evaluation of the image content annotation system by using the multilayer neural networks and the nearest neighbour classifier. The region growing segmentation is used to separate objects, the Hu moments, Legendre moments and Zernike moments which are used in as feature descriptors for the image content characterization and annotation.The ETH-80 database image is used in the experiments here. The best annotation rate is achieved by using Legendre moments as feature extraction method and the multilayer neural network as a classifier. Keywords-Image annotation; region growing segmentation; multilayer neural network classifier; nearest neighbour classifier;
viXra, 2012
The aim of this work is to present a system for recognizing isolated Arabic printed characters. T... more The aim of this work is to present a system for recognizing isolated Arabic printed characters. This system goes through several stages: preprocessing, feature extraction and classification. Zernike moments, invariant moments and Walsh transformation are used to calculate the features. The classification is based on multilayer neural networks. A recognition rate of 98% is achieved by using Zernike moments.
This document presents a system in order to annotate image content by using the region growing se... more This document presents a system in order to annotate image content by using the region growing segmentation, as a method to separate different objects within an image, and the multilayer neural network to classify these objects and to find the appropriate keywords for them. In many applications, different kinds of moments have been used as features to classify the images and objects’ shapes. The Hu moments, Legendre moments and Zernike moments are used, in this paper, as features to describe an image. The experiments are done through using ETH-80 database images. General Terms Neural Networks, Moments, Image Annotation.
The object image annotation problem is basically a classification problem and there are many diff... more The object image annotation problem is basically a classification problem and there are many different modeling approaches for the solution. These approaches can be classified into two main categories such as generative and discriminative. An ideal classifier should combine these two complementary approaches. In this paper, we present a method achieving this combination by using the discriminative power of the neural networks and the generative nature of Bayesian networks. The evaluation of the proposed method on three typical image’s database has shown some success in automatic image annotation.
TELKOMNIKA Indonesian Journal of Electrical Engineering
In this paper we study the problem of combining low-level visual features for semantic image anno... more In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.
International Journal of Advanced Computer Science and Applications, 2013
In order to improve the recognition rate, this document proposes an automatic system to recognize... more In order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of 3 classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments and Hu moments are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method and each single classification method are compared with our approach to show its robustness.
2012 6th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), 2012
ABSTRACT In this paper, we propose a hybrid approach based on neural networks and the combination... more ABSTRACT In this paper, we propose a hybrid approach based on neural networks and the combination of the classic Hu & Zernike moments joined with Geodesic descriptors. To be able to keep the maximum amount of information that are given by the color of the image, we have calculated Zernike & Hu for each color level. On the other side, geodesic descriptors are applied directly to binary images, and so we can have more information about the general shape of the object. The extracted vectors are put together to form a unique input data to the Neural network. The experimental results showed that the recognition rate of the ANN shape recognition based on the combination of Hu, Zernike & Geodesic descriptors results are noticeably improved. It is also important to note the robustness of the proposed system against the existence of noise, the luminance change, and geometric distortion.
International Journal of Advanced Computer Science and Applications, 2013
International Journal of Advanced Computer Science and Applications, 2013
The majority of Tifinagh OCR presented in the literature does not exceed the scope of simulation ... more The majority of Tifinagh OCR presented in the literature does not exceed the scope of simulation software such as Matlab. In this work, the objective is to compare the classification data mining tool for Tifinagh character recognition. This comparison is performed in a working environment using an Oracle database and Oracle Data Mining tools (ODM) to determine the algorithms that gives the best Recognition rates (rate / time).
International Journal of Computer Applications, 2014
Most of the reported works in the field of character recognition systems achieve modest results b... more Most of the reported works in the field of character recognition systems achieve modest results by using a single method for calculating the parameters of the character image and a single approach in the classification phase of the system. So, in order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of some classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments, Hu moments, Walsh transform, GIST and texture are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the Bayesian network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method with each single classification method are compared with our approach to show its robustness. A recognition rate of 100 % is achieved by using some combined descriptors and classifiers.
The aim of this work is to present a system for recognizing isolated Arabic printed characters. T... more The aim of this work is to present a system for recognizing isolated Arabic printed characters. This system goes through several stages: preprocessing, feature extraction and classification. Zernike moments, invariant moments and Walsh transformation are used to calculate the features. The classification is based on multilayer neural networks. A recognition rate of 98% is achieved by using Zernike moments.
2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV), 2016
Ijca Special Issue on Software Engineering Databases and Expert Systems, Sep 17, 2012
International Journal of Computer Applications, Nov 15, 2013
This paper provides an approach to automatically recognize the Tifinagh characters. The proposed ... more This paper provides an approach to automatically recognize the Tifinagh characters. The proposed recognition system is based on Texture, Walsh transformation and GIST descriptors as feature extraction methods while the Bayesian Networks are used as a classifier. A comparative study between the Texture descriptor, Walsh transformation and GIST descriptor is given. The experimental results are obtained using a character database of isolated Amazigh characters. A recognition rate of 98.18% is achieved using GIST descriptors.
This paper provides an approach to automatically recognize the Tifinagh characters. The proposed ... more This paper provides an approach to automatically recognize the Tifinagh characters. The proposed recognition system is based on Texture, Walsh transformation and GIST descriptors as feature extraction methods while the Bayesian Networks are used as a classifier. A comparative study between the Texture descriptor, Walsh transformation and GIST descriptor is given. The experimental results are obtained using a character database of isolated Amazigh characters. A recognition rate of 98.18 % is achieved using GIST descriptors.
Journal of Physics: Conference Series, 2021
Accurate monitoring of agricultural lands and crop types is a crucial tool for sustainable food p... more Accurate monitoring of agricultural lands and crop types is a crucial tool for sustainable food production. Therefore, to provide reliable and updated crop maps, the improvement of satellite image classification approaches is essential. In this context, machine learning algorithms present a potential tool for efficient and effective classification of remotely sensed data. The main strengths of machine learning algorithms are the capacity to handle data of high dimensionality, and mapping classes characterized by strong complex dynamics. The main objective of this work was to develop a new synergistic approach for crop discrimination in the semi-arid region of Chichaoua province, located in the Marrakesh-Safi region, Morocco, using high spatio-temporal resolution imagery and a multiple combination of machine learning classifiers. This approach was developed based on 10m spatial resolution open access Sentinel-2 (S2) images and machine learning algorithms. The atmospherically correcte...
Pattern Recognition and Image Analysis, 2016
A large percentage of photos on the Internet cannot be reached by search engines because of the s... more A large percentage of photos on the Internet cannot be reached by search engines because of the semantic gap due to the absence of textual meta data. Despite of decades of research, neither model based approaches can provide quality annotation to images. Many segmentation algorithms use a low level predi cates to control the homogeneity of the regions. So, the resulting regions are not always being semantically compact. The first proposed approach to resolve this problem is to regroup the adjacent region of image. Many features extraction method and classifiers are also used singly, with modest results, for automatic image annotation. The second proposed approach is to select and combine together some efficient descriptors and classifiers. This document provides a hybrid semantic annotation system that combines both approaches in hopes of increasing the accuracy of the resulting annotations. The color histograms, Texture, GIST and invariant moments, used as features extraction methods, are combined together with multi class support vec tor machine, Bayesian networks, Neural networks and nearest neighbor classifiers, in order to annotate the image content with the appropriate keywords. The accuracy of the proposed approach is supported by the good experimental results obtained from two image databases (ETH 80 and coil 100 databases).
Detection recognition and analysis of human faces are some of the most interesting subjects of co... more Detection recognition and analysis of human faces are some of the most interesting subjects of computer vision, especially in a video stream. In the last few years, the algorithms of learning facial features have evolved in many ways, and since the capacity of detecting and reading the human facial features is extremely powerful and is becoming more and more efficient, it will lead us to detect a certain specific data that can be used for security purposes. On the other hand, the appearance of the special bases of command and coordination that enter in the political safe cities projects makes it a huge deal of interest to use these models for empowering those cameras to detect and identify target people. In This article, we propose a real-time intelligent monitoring system that has as objective to detect a specific accuracy of figures of wanted people that had already been studied and learned by a pre-trained model that describe the data in the learning stage through extracting feat...
Abstract—The explosive growth of image data leads to the research and development of image conten... more Abstract—The explosive growth of image data leads to the research and development of image content searching and indexing systems. Image annotation systems aim at annotating automatically animage with some controlled keywords that can be used for indexing and retrieval of images. This paper presents a comparative evaluation of the image content annotation system by using the multilayer neural networks and the nearest neighbour classifier. The region growing segmentation is used to separate objects, the Hu moments, Legendre moments and Zernike moments which are used in as feature descriptors for the image content characterization and annotation.The ETH-80 database image is used in the experiments here. The best annotation rate is achieved by using Legendre moments as feature extraction method and the multilayer neural network as a classifier. Keywords-Image annotation; region growing segmentation; multilayer neural network classifier; nearest neighbour classifier;
viXra, 2012
The aim of this work is to present a system for recognizing isolated Arabic printed characters. T... more The aim of this work is to present a system for recognizing isolated Arabic printed characters. This system goes through several stages: preprocessing, feature extraction and classification. Zernike moments, invariant moments and Walsh transformation are used to calculate the features. The classification is based on multilayer neural networks. A recognition rate of 98% is achieved by using Zernike moments.
This document presents a system in order to annotate image content by using the region growing se... more This document presents a system in order to annotate image content by using the region growing segmentation, as a method to separate different objects within an image, and the multilayer neural network to classify these objects and to find the appropriate keywords for them. In many applications, different kinds of moments have been used as features to classify the images and objects’ shapes. The Hu moments, Legendre moments and Zernike moments are used, in this paper, as features to describe an image. The experiments are done through using ETH-80 database images. General Terms Neural Networks, Moments, Image Annotation.
The object image annotation problem is basically a classification problem and there are many diff... more The object image annotation problem is basically a classification problem and there are many different modeling approaches for the solution. These approaches can be classified into two main categories such as generative and discriminative. An ideal classifier should combine these two complementary approaches. In this paper, we present a method achieving this combination by using the discriminative power of the neural networks and the generative nature of Bayesian networks. The evaluation of the proposed method on three typical image’s database has shown some success in automatic image annotation.
TELKOMNIKA Indonesian Journal of Electrical Engineering
In this paper we study the problem of combining low-level visual features for semantic image anno... more In this paper we study the problem of combining low-level visual features for semantic image annotation. The problem is tackled with a two different approaches that combines texture, color and shape features via a Bayesian network classifier. In first approach, vector concatenation has been applied to combine the three low-level visual features. All three descriptors are normalized and merged into a unique vector used with single classifier. In the second approach, the three types of visual features are combined in parallel scheme via three classifiers. Each type of descriptors is used separately with single classifier. The experimental results show that the semantic image annotation accuracy is higher when the second approach is used.
International Journal of Advanced Computer Science and Applications, 2013
In order to improve the recognition rate, this document proposes an automatic system to recognize... more In order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of 3 classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments and Hu moments are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method and each single classification method are compared with our approach to show its robustness.
2012 6th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), 2012
ABSTRACT In this paper, we propose a hybrid approach based on neural networks and the combination... more ABSTRACT In this paper, we propose a hybrid approach based on neural networks and the combination of the classic Hu & Zernike moments joined with Geodesic descriptors. To be able to keep the maximum amount of information that are given by the color of the image, we have calculated Zernike & Hu for each color level. On the other side, geodesic descriptors are applied directly to binary images, and so we can have more information about the general shape of the object. The extracted vectors are put together to form a unique input data to the Neural network. The experimental results showed that the recognition rate of the ANN shape recognition based on the combination of Hu, Zernike & Geodesic descriptors results are noticeably improved. It is also important to note the robustness of the proposed system against the existence of noise, the luminance change, and geometric distortion.
International Journal of Advanced Computer Science and Applications, 2013
International Journal of Advanced Computer Science and Applications, 2013
The majority of Tifinagh OCR presented in the literature does not exceed the scope of simulation ... more The majority of Tifinagh OCR presented in the literature does not exceed the scope of simulation software such as Matlab. In this work, the objective is to compare the classification data mining tool for Tifinagh character recognition. This comparison is performed in a working environment using an Oracle database and Oracle Data Mining tools (ODM) to determine the algorithms that gives the best Recognition rates (rate / time).
International Journal of Computer Applications, 2014
Most of the reported works in the field of character recognition systems achieve modest results b... more Most of the reported works in the field of character recognition systems achieve modest results by using a single method for calculating the parameters of the character image and a single approach in the classification phase of the system. So, in order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of some classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments, Hu moments, Walsh transform, GIST and texture are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the Bayesian network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method with each single classification method are compared with our approach to show its robustness. A recognition rate of 100 % is achieved by using some combined descriptors and classifiers.
The aim of this work is to present a system for recognizing isolated Arabic printed characters. T... more The aim of this work is to present a system for recognizing isolated Arabic printed characters. This system goes through several stages: preprocessing, feature extraction and classification. Zernike moments, invariant moments and Walsh transformation are used to calculate the features. The classification is based on multilayer neural networks. A recognition rate of 98% is achieved by using Zernike moments.
2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV), 2016
Ijca Special Issue on Software Engineering Databases and Expert Systems, Sep 17, 2012
International Journal of Computer Applications, Nov 15, 2013
This paper provides an approach to automatically recognize the Tifinagh characters. The proposed ... more This paper provides an approach to automatically recognize the Tifinagh characters. The proposed recognition system is based on Texture, Walsh transformation and GIST descriptors as feature extraction methods while the Bayesian Networks are used as a classifier. A comparative study between the Texture descriptor, Walsh transformation and GIST descriptor is given. The experimental results are obtained using a character database of isolated Amazigh characters. A recognition rate of 98.18% is achieved using GIST descriptors.