hela mahersia | Kuningan - Academia.edu (original) (raw)

Papers by hela mahersia

ABSTRACT Classification of texture images invariant to similarity transformations (shift, rotatio... more ABSTRACT Classification of texture images invariant to similarity transformations (shift, rotation and scaling) is regarded as one of difficult tasks in image processing. In this paper, we present a theoretically and computationally efficient approach for rotation invariant texture classification. The feature extraction for a given image involves applying the log-polar transform to eliminate the rotation effects, followed by the ridgelet transform. The method is tested with 4670 randomly rotated samples of 70 texture classes obtained from the Brodatz and the VisTex albums. Comparative study results show that our method is highly efficient in rotation invariant texture classification.

Content-based image retrieval is an active and fast advancing research area since the 1990s as a ... more Content-based image retrieval is an active and fast advancing research area since the 1990s as a result of advances in the Internet and new digital image sensor technologies. However, many challenging research problems continue to attract researchers from multiple disciplines. Content-based image retrieval uses the visual contents of an image as features to represent and index the image to be searched from large scale image databases. The quality of the selected features relies mainly on the degree of the invariance property that is ensured under acceptable manipulations. This paper proposes an efficient method for compactly representing color and texture features and combining them for image retrieval. The performance of retrieval based on these compact descriptors obtained by the proposed techniques is analyzed and tested on wang database images yielding satisfactory accuracy rates. A comparative study demonstrated that the developed feature extraction scheme outperformed the other schemes being compared with.

InTech eBooks, Aug 9, 2011

Engineering Applications of Artificial Intelligence, Feb 1, 2015

ABSTRACT Facial expression recognition has recently become a challenging research area. Its appli... more ABSTRACT Facial expression recognition has recently become a challenging research area. Its applications include human–computer interfaces, human emotion analysis, and medical care and cure.In this paper, we present a new challenging method to recognize seven universal emotional expressions, which are happiness, neutral, angry, disgust, sadness, fear and surprise. In our approach, we identify the user׳s facial expressions from the input images, using statistical features extracted from the steerable pyramid decomposition, and classified with a Bayesian regularization neural network. The evaluation of the proposed approach in terms of recognition accuracy is achieved using two universal databases, the Japanese Female Facial Expression database and the Cohn–Kanade facial expression database. The overall accuracy rate reaches 93.33% for the first database and is about 98.13% for the second one. These results show the effectiveness of the steerable proposed algorithm.

International Journal of Image and Graphics, Apr 1, 2012

Iris recognition has been recently given greater attention in human identification and it is beco... more Iris recognition has been recently given greater attention in human identification and it is becoming increasingly an active topic in research. This paper presents a novel iris recognition method based on multi-channel Gabor filtering and uniform local binary patterns (ULBP). First, the eye image is processed in order to obtain a segmented and normalized eye image by applying Hough transform and polar transformation. Second, the iris image is analyzed by Gabor filters to extract the global features of texture details. Then, ULBP operators are applied in each transformed image to describe the local arrangement of iris texture patterns. Next, the obtained representation is partitioned in blocks. Finally, we have encoded the local relationships between statistical measures computed in blocks to form a template of 240 bytes. We estimate the similarity between irises by computing the modified Hamming distance between templates. Tests were carried out on CASIA v3 iris database. Experimental results illustrate the effectiveness and robustness of ULBP to extract rich local and global information of iris texture when combined with simultaneously multi-blocks and multi-channel method. The comparative evaluations illustrate the good discriminative properties of extracted features for iris recognition.

2022 4th IEEE Middle East and North Africa COMMunications Conference (MENACOMM)

International Review on Computers and Software, Aug 31, 2013

Local Binary Patterns (LBP) is a local approach widely used in the field of texture analysis. Gen... more Local Binary Patterns (LBP) is a local approach widely used in the field of texture analysis. Generally, the LBP algorithm is applied on the original texture. Our contribution, as presented in this paper, will be to apply this algorithm on the sub bands resulting from the wavelet transform. This allows characterising texture on various resolution levels. As training bases, we used a set of 30 elements extracted from the Brodatz album and a set of 40 elements extracted from the Vistex album. To test the invariance of the proposed method, several tests have been carried out on textures with rotation changes or scale changes, and many parameters have been tested including the radius of the LBP, the distance measure and the wavelet's nature. These results demonstrate the effectiveness of our characterization method in texture image classification experiments.

2022 19th International Multi-Conference on Systems, Signals & Devices (SSD), May 6, 2022

International Journal of Advanced Computer Science and Applications, 2016

Breast cancer is one of the most deadly cancers in the world, especially among women. With no ide... more Breast cancer is one of the most deadly cancers in the world, especially among women. With no identified causes and absence of effective treatment, early detection remains necessary to limit the damages and provide possible cure. Submitting women with family antecedent to mammography periodically can provide an early diagnosis of breast tumors. Computer Aided Diagnosis (CAD) is a powerful tool that can help radiologists improving their diagnostic accuracy at earlier stages. Several works have been developed in order to analyze digital mammographies, detect possible lesions (especially masses and microcalcifications) and evaluate their malignancy. In this paper a new approach of breast microcalcifications diagnosis on digital mammograms is introduced. The proposed approach begins with a preprocessing procedure aiming artifacts and pectoral muscle removal based on morphologic operators and contrast enhancement based on galactophorous tree interpolation. The second step of the proposed CAD system consists on segmenting microcalcifications clusters, using Generalized Gaussian Density (GGD) estimation and a Bayesian backpropagation neural network. The last step is microcalcifications characterization using morphologic features which are used to feed a neuro-fuzzy system to classify the detected breast microcalcifications into benign and malignant classes.

Abstract. In this paper, we investigated an ensemble neural network for the prediction of oil pri... more Abstract. In this paper, we investigated an ensemble neural network for the prediction of oil prices. Daily data from 1999 to 2012 were used to predict the West Taxes, Intermediate. Data were separated into four phases of training and testing using different percentages and obtained seven sub-datasets after implementing different attribute selection algorithms. We used three types of neural networks: Feed forward, Recurrent and Radial Basis Function networks. Finally a good ensemble neural network model is formulated by the weighted average method. Empirical results illustrated that the ensemble neural network outperformed other models.

Proceedings of the Symposium on Applied Computing, 2017

In this paper, we explore the use of the discrete orthogonal Stockwell transform (DOST) in image ... more In this paper, we explore the use of the discrete orthogonal Stockwell transform (DOST) in image watermarking by proposing a blind medical image watermarking (MIW) method based on multi-resolution representation that proceeds by embedding the watermark within the high frequency subbands of the 2D DOST representation of the cover image. Experimental results show that the proposed method improved the transparency of watermarking artifacts in comparison with other works and achieved a good compromise between fidelity and capacity.

2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2017

In this paper, we extend the use of the Discrete Orthogonal Stockwell Transform (DOST) by introdu... more In this paper, we extend the use of the Discrete Orthogonal Stockwell Transform (DOST) by introducing a blind reversible and fragile medical image watermarking (MIW) method for image integrity checking. 2D DOST is first applied to the host image, the watermark is inserted in the high frequency coefficients based on the Difference Expansion (DE) technique. The extraction process provides host image retrieval after watermark removal. Experimental results show that the method achieved a high visual quality for marked images resulting in a better compromise between fidelity a nd capacity.

— Image denoising is one of the most significant tasks especially in medical image processing, wh... more — Image denoising is one of the most significant tasks especially in medical image processing, where the original images are of poor quality due the noises and artifacts introduces by the acquisition systems. In this paper, we propose a new image denoising scheme by modifying the wavelet coefficients using soft-thresholding method, we present a comparative study of different wavelet denoising techniques for CT images and we discuss the obtained results. The denoising process rejects noise by thresholding in the wavelet domain. The performance is evaluated using Peak Signal-to-Noise Ratio (PSNR) and Mean Squared Error (MSE). Finally, Gaussian filter provides better PSNR and lower MSE values. Hence, we conclude that this filter is an efficient one for preprocessing medical images.

2018 15th International Multi-Conference on Systems, Signals & Devices (SSD), 2018

Bone sarcoma, usually known as bone cancer, is a rare type of cancer that refers to an abnormal g... more Bone sarcoma, usually known as bone cancer, is a rare type of cancer that refers to an abnormal growth of tissue inside the bone, with high probability to spread to other parts of the body. It commonly affects children, teenagers and young adults. As for all other types of cancer (breast, lung, prostate, stomach, brain …), there are no identified causes for bone cancer. Therefore, only an early detection could help increasing the chances to survive a bone sarcoma. The association of medical imaging modalities (such as X-ray, MRI and CT imaging) with image processing techniques can provide more accuracy while detection eventual bone tumors. In this paper, we introduced a new method for sarcoma diagnosis, using a Generalized Gaussian Density analysis (GGD). The process starts by generating sub-images of a given size from the processed bone MRI and conducting a GGD analysis on each of the sub-images. Then, a region of interest(ROI) corresponding to the sub-images with the highest value...

2020 17th International Multi-Conference on Systems, Signals & Devices (SSD), 2020

Lung nodules are generally higher indicators of lung cancer. Detected at an early stage, their tr... more Lung nodules are generally higher indicators of lung cancer. Detected at an early stage, their treatment could be easier and patient chances for survival are improved. This research aims to establish a methodology for the automated identification of lung nodules using image processing and pattern recognition techniques. The automatic system that we propose in this paper includes a pre-processing stage, a nodule characterization stage and a classification stage. The proposed preprocessing system aims to delimit the lung tissue by deleting all the unnecessary regions. The characterization process is based mainly on the analysis of the textural properties of the nodules. The gaussian density calculation in the wavelet domain allows for an efficient segmentation of the current nodules. Then, a comparative classification method based on SVM classifier, bayesian regularization networks and ANFIS classifier, on the LIDC database, is proposed, showing the robustness of the approach proposed.

Biometric methods, which identify people based on physical or behavioural characteristics, are of... more Biometric methods, which identify people based on physical or behavioural characteristics, are of interest because people cannot forget or lose their physical characteristics in the way that they can lose passwords or identity cards. Among these biometric methods, iris is currently considered as one of the most reliable biometrics because of its unique texture‘s random variation. Moreover, iris is proved to be well protected from the external environment behind the cornea, relatively easy to acquire and stable all over the person’s life. For all of these reasons, iris patterns become interesting as an alternative approach to reliable visual recognition of persons. This recognition system involves four main modules: iris acquisition, iris segmentation and normalization, feature extraction and encoding and finally matching. However, we noticed that almost all the iris recognition systems proceed without controlling the iris image’s quality. Naturally, poor image’s quality degrades sig...

Classification of distorted texture images is a challenging and important problem in real world i... more Classification of distorted texture images is a challenging and important problem in real world image analysis and understanding. This paper proposes a new texture characterization method which is robust to geometric distortions, including rotation and scale changes. The rotation- and scale-invariant feature extraction for a given image involves applying the log-polar transform to eliminate the rotation and scale effects, followed by the ridgelet transform. In the experiments, the K-nearest neighborhood classifier is employed, using Euclidian and Manhattan distances to classify two sets of 30 and 40 distinct natural textures selected from the Brodatz and the VisTex albums. The experimental results, based on different test data sets for images with different orientations and scales, show that the proposed classification scheme using log-polar ridgelet signatures outperforms texture classification based on log-polar and wavelet transforms. Its overall accuracy rate reaches 100% for or...

2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2020

Breast cancer represents the highest percentage of cancers that affect women with 450000 deaths e... more Breast cancer represents the highest percentage of cancers that affect women with 450000 deaths each year in the world. In Tunisia, it represents 30% of cancers diagnosed in women, thus occupying the first place in front of that of the cervix. In fact, it is important to identify breast cancer at an initial phase to decrease the death rate. In mammograms, the automatic mass recognition and classification remains a significant challenge and plays a critical role in helping radiologists to make a precise diagnosis. Recent improvements in the analysis of biomedical images using neural networks based on deep learning can be utilized to improve the CAD systems (computer-assisted diagnostic) performance. This paper presents the main deep learning approaches used for mammographic images, which can help us to identify research problems in current studies.

New Perspectives on Electric Vehicles [Working Title]

This chapter deals with a design of a new speed control method using artificial intelligence tech... more This chapter deals with a design of a new speed control method using artificial intelligence techniques applied to an autonomous electric vehicle. In this research, we develop an Advanced Driver Assistance System (ADAS) which aims to enhance the driving manner and the safety, especially when traveling too fast. The proposed model is a complete end-to-end vehicle speed system controller that proceeds from a detected speed limit sign to the regulation of the motor’s speed. It recognizes the speed limit signs before extracting from them, a speed information that will be sent, as reference, to a NARMA-L2 based controller. The study is developped specially for electric vehicle using Brushless Direct Current (BLDC) motor. The simulation results, implemented using Matlab-Simulink, show that the speed of the electric vehicle is controlled successfully with different speed references coming from the image processing unit.