Shaheera Rashwan | Tanta University (original) (raw)

Papers by Shaheera Rashwan

2022 32nd International Conference on Computer Theory and Applications (ICCTA)

Machine Learning and Applications: An International Journal

Prediction of quality and consumers’ preferences is essential task for food producers to improve ... more Prediction of quality and consumers’ preferences is essential task for food producers to improve their market share and reduce any gap in food safety standards. In this paper, we develop a machine learning method to predict yogurt preferences based on the sensory attributes and analysis of samples’ images using image processing texture and color feature extraction techniques. We compare three unsupervised ML feature selection techniques (Principal Component Analysis and Independent Component Analysis and t-distributed Stochastic Neighbour Embedding) with one supervised ML feature selection technique (Linear Discriminant Analysis) in terms of accuracy of classification. Results show the efficiency of the supervised ML feature selection technique over the traditional feature selection techniques.

2022 11th International Conference on Information Communication and Applications (ICICA)

International Journal of Image and Graphics, 2021

The main objective of hyper/multispectral image fusion is producing a composite color image that ... more The main objective of hyper/multispectral image fusion is producing a composite color image that allows for an appropriate visualization of the relevant spatial and spectral information. In this paper, we propose a general framework for spectral weighting-based image fusion. The proposed methodology relies on weight updates conducted using nature-inspired algorithms and a goodness-of-fit criterion defined as the average root mean square error. Simulations on four public data sets and a recent Landsat 8 image of Brullus Lake, Egypt, as an area of study prove the efficiency of the proposed framework. The purpose of the study is to present a framework of multi-band image fusion that produces a fused image of high quality to be further used in computer processing and the results show that the image produced by the presented framework has the highest quality compared with some of the state-of-the art algorithms. To prove the increase in the image quality, we used general quality metrics ...

International Journal of Image Processing and Vision Science

Coarse resolution captured in remote sensing causes the combination of different materials in one... more Coarse resolution captured in remote sensing causes the combination of different materials in one pixel, called the mixed pixel. Spectral unmixing estimates the combination of endmembers in mixed pixels and their corresponding abundance maps in the Hyper/Multi spectral image. In this paper, a nonlinear spectral unmixing based on semi-supervised fuzzy clustering is proposed. First, pure pixels (endmembers) using Vertex Component Analysis (VCA) are extracted and those pixels are the labelled pixels where the membership value of each is 1 for the corresponding endmember and 0 for the others. Second, the semi-supervised fuzzy clustering is applied to find the membership matrix defining the fraction of the endmember in each mixed pixel and hence extract the abundance maps. The experiments were conducted on both synthetic data such as the Legendre data and real data such as Jasper Ridge data. The non-linearity of the Legendre data was performed by the Fan model on different signal-tonoise...

To acquire detection performance required for an operational system in the detection for satellit... more To acquire detection performance required for an operational system in the detection for satellite image for environmental change, it is necessary to use multiple images over years to know the environmental changes over years. This paper describes a method for decision-level fusion technique where the fusion can compensate for correlation among images. The fusion is done using possibilistic combiners based on T-norms families that better represent the correlation of images. This technique was applied to Nile River Delta, Egypt (1973, 1987). These images show the dramatic urban growth within the Nile River delta and the expansion of agriculture into adjoining desert areas.

In this paper we are concerned with the problem of detecting the outliers, i.e, the exceptional t... more In this paper we are concerned with the problem of detecting the outliers, i.e, the exceptional tuple values breaking the fuzzy dependency. Using the typology of fuzzy rules, we distinguish three kinds of Fuzzy Functional Dependency and propose a general framework for extending the definition of Fuzzy Functional Dependency. According to a semantical view of fuzzy rules for handling exceptions, this framework is based on the graded certainty/possibility of the resemblance of the consequent attributes rather than the graduality of the resemblance of these attributes. Of primary interest is the exceptionality computation, which is represented by the Fuzzy Certainty Rule Dependency or the Fuzzy Possibility Rule Dependency proposed in the paper, and which will be taken in consideration by both the designer, and the database user. A combined approach is proposed in the paper to combine both the Fuzzy Certainty Rule Dependency and the Fuzzy Possibility Rule Dependency. Key-Words: Fuzzy Fun...

International Journal of Computer Applications, 2012

One of the new and promising algorithms appeared in the area of image segmentation is the Fuzzy C... more One of the new and promising algorithms appeared in the area of image segmentation is the Fuzzy C-Means algorithm. This algorithm has been used in many applications such as: data analysis, pattern recognition, and image segmentation. It has the advantages of producing high quality segmentation compared to the other available algorithms. Our work in this paper will be based on the Fuzzy C-Means algorithm and by adding the relational fuzzy notion to it so as to enhance its performance especially in the area of 2-D gel images. The simulation results of comparing the Fuzzy C-Means (FCM) and the proposed algorithm Relational Fuzzy CMeans (RFCM) on 2D gel images acquired from: Human leukemias, HL-60 cell lines and Fetal alcohol syndrome (FAS) show the improvement achieved by the proposed algorithm in overcoming the over-segmentation error.

Multi sensor fusion is an important component of applications for systems that use correlated dat... more Multi sensor fusion is an important component of applications for systems that use correlated data from multiple sensors to determine the state of a system. As the state of the system being monitored and many sensors are affected by the environmental conditions changing with time, the multi sensor fusion requires a correlation-dependent approach. The behavior of this approach should vary according to the correlation parameter. In this paper, we compare our possibilistic correlation-dependent fusion approach (PCDF) with the possiblistic combiner Dempster-Shafer. We focus in this paper on the mathematical background of this approach so that it can be used in many useful applications.

Classification of hyperspectral images is a hot topic in remote sensing field because of its imme... more Classification of hyperspectral images is a hot topic in remote sensing field because of its immense dimensionality. Several machine learning approaches had been effectively proposed for hyperspectral image processing. Multiple kernel learning (MKL) approaches are the most used techniques that have been promoted to improve the adaptability of kernel based learning machine. In this paper, an adaptive MKL approach is promoted for the classification of hyperspectral imagery problem. The core idea in the introduced algorithm is to optimize the convex combinations of the given base kernels during the training process of Self-Organizing Maps. Diverse types of kernel functions are used. The performance of the classifier based on the choice of the kernel function and its variables, Benchmark hyperspectral datasets are used. The experimental results demonstrate that the introduced MKLSOM learning algorithm gives a comparative solution to the state-of-the-art algorithms.

International Journal of Computer Applications, 2020

Many specialized software programs are available for processing two dimensional gel electrophores... more Many specialized software programs are available for processing two dimensional gel electrophoresis (2-DGE) images. However, the anomalies existing in these images make the achievement of a reliable system for 2-DGE image analysis still difficult to reach. In this paper, we propose a new preprocessing technique applied to 2-DGE images. The new technique is based on image inpainting using Mumford Shah Euler Lagrange to discard anomalies such as vertical and horizontal streaking from these images. We also present a comparison of the analysis of 2-DGE images inpainted by the proposed technique and non-inpainted images using the known commercial software Delta2D. We compute the F-measure in both cases for three different 2-DGE images. The degree of improvement in F-measure reaches 18.5% in first image and 5.9% in second image and 3.8% in third image. Our new 2D Gel image preprocessing method based on Mumford Shah inpainting shows a significant improvement when comparing analysis of inpa...

An important issue in the analysis of two-dimensional electrophoresis images is the detection and... more An important issue in the analysis of two-dimensional electrophoresis images is the detection and quantification of protein spots. The main challenges in the segmentation of 2DGE images are to separate overlapping protein spots correctly and to find the abundance of weak protein spots. To enable comparison of protein patterns between different samples, it is necessary to match the patterns so that homologous spots are identified. In this paper, we describe a new robust technique to segment and model the different spots present in the gels. The Watershed segmentation algorithm is modified to handle the problem of over segmentation by initially partitioning the image to mosaic regions using the composition of fuzzy relations. The experimental results showed the effectiveness of the proposed algorithm to overcome the over segmentation problem associated with the available algorithm. We also use a wavelet denoising function to enhance the quality of the segmented image. The parameters o...

Summary An important issue in the analysis of two-dimensional electrophoresis images is the detec... more Summary An important issue in the analysis of two-dimensional electrophoresis images is the detection and quantification of protein spots. The main challenges in the segmentation of 2DGE images are to separate overlapping protein spots correctly and to find the abundance of weak protein spots. To enable comparison of protein patterns between different samples, it is necessary to match the patterns so that homologous spots are identified. In this paper we describe a new robust technique to segment and model the different spots present in the gels. The watershed segmentation algorithm is modified to handle the problem of over segmentation by initially partitioning the image to mosaic regions using the composition of fuzzy relations. The experimental results showed the effectiveness of the proposed algorithm to overcome the over segmentation problem associated with the available algorithms.

Hyperspectral imaging (HSI) captures a densely sampled spectral response of a scene object over a... more Hyperspectral imaging (HSI) captures a densely sampled spectral response of a scene object over a broad spectrum including invisible spectra such as ultra-violet (UV) and near-infrared(NIR). In this paper, we propose a new Expectation-Maximization (EM) classification approach for hyperspectral images. The new approach is based on Haar discrete wavelet and histogram equalization. The performance of the proposed method was assessed by carrying out experiments on the AVIRIS dataset. The results show a significant improvement in classification accuracy and time when compared with the results obtained by the conventional EM algorithm.

In proteomics 2-dimensional SDS-polyacrylamide gel electrophoresis (2D-PAGE) is the most widely u... more In proteomics 2-dimensional SDS-polyacrylamide gel electrophoresis (2D-PAGE) is the most widely used method for analyzing protein mixtures qualitatively. There are, however, a lot of noise and measurement biases which needs to be accounted for both in the localization of spots as well as in the quantitative measurement of protein expression. Previous techniques for denoising 2D gels are based on thresholding, smoothing and spot recognition. Wavelet transformations have also been applied to denoise 2D gels, however these techniques are typically in the frequency domain and they tend to shift spots slightly. In this paper, we improve the protein spot detection process by wavelet de-noising based on genetic algorithm.

International Journal of Computational Vision and Robotics

Journal of Applied Remote Sensing

Abstract. Hyperspectral image (HSI) analysis is a growing area in the community of remote sensing... more Abstract. Hyperspectral image (HSI) analysis is a growing area in the community of remote sensing, particularly with images exhibiting high spatial and spectral resolutions. Multiple kernel learning (MKL) has been proposed and found to classify HSIs efficiently owing to its capability for handling diverse feature fusion. However, constructing base kernels, selecting key kernels, and adjusting their contributions to the final kernel remain major challenges for MKL. We propose a scheme to generate effective base kernels and optimize their weights, which represent their contribution to the final kernel. In addition, both spatial and spectral information are utilized to improve the classification accuracy. In the proposed scheme, the spatial features of HSIs are introduced through multiscale feature representations that preserve the relationship between the classification process and the pixel context. MKL and self-organizing maps (SOMs) are integrated and used for the unsupervised classification of HSIs. The weights of both the base kernels and neural networks are simultaneously optimized in an unsupervised manner. The results indicate that the proposed MKL-SOM scheme outperforms state-of-the-art algorithms, particularly when applied to large HSIs. Moreover, its ability to fuse multiscale features, especially in large HSIs, is useful for various analysis tasks.

International Journal of Image and Data Fusion

ABSTRACT High magnification optical cameras, such as microscopes or macro-photography, cannot cap... more ABSTRACT High magnification optical cameras, such as microscopes or macro-photography, cannot capture an object that is totally in focus. In this case, image acquisition is done by capturing the object/scene with the camera using a set of images with different focuses, then fusing to produce an ‘all-in-focus’ image that is clear everywhere. This process is called multi-focus image fusion. In this paper, a method named Watershed on Intensity Hue Saturation (WIHS) is proposed to fuse multi-focus images. First, the defocused images are fused using IHS image fusion. Then the marker controlled watershed segmentation algorithm is utilized to segment the fused image. Finally, the Sum-Modified of Laplacian is applied to measure the focus of multi-focus images on each region and the region with higher focus measure is chosen from its corresponding image to compute the all-in- focus resulted image. The experiment results show that WIHS has best performance in quantitative comparison with other methods.

Journal of Real-Time Image Processing

AbstractSpectral unmixing algorithms are commonly used in processing of hyperspectral images to i... more AbstractSpectral unmixing algorithms are commonly used in processing of hyperspectral images to identify the elemental components, called end-members, and their corresponding information in each pixel of the image. However, these algorithms are computationally intensive and can become a bottleneck for remote sensing hyperspectral image processing, especially in large aerial imagery processing centers. This paper, explores the use of massive parallel processing graphical processing unit to speed up the multi kernel self-organizing map (MKSOM) unmixing algorithm. MKSOM is based on artificial neural networks, which makes it suitable to be efficiently parallelized. Two real benchmark hyperspectral images; AVIRIS Cuprite and Brullus are used to evaluate the performance of the parallel algorithm. The experimental results show that the proposed implementation is appropriated for real-time hyperspectral remote sensing applications due to a very small worst case parallel execution time (0.83 s when the number of classes is less than 9) which makes it feasible to be integrated as on-board processing on any Hyperspectral remote sensors. Our parallel technique achieved a significant speedup compared with a multi-threaded CPU implementation applied on the same hyperspectral image. The results showed a speedup of 93.46 × for SOM size of 256 and trained for 100 epochs on medium-sized HSI such as AVIRIS Cuprite.

IEEE Geoscience and Remote Sensing Letters

The problem of band selection (BS) is of great importance to handle the curse of dimensionality f... more The problem of band selection (BS) is of great importance to handle the curse of dimensionality for hyperspectral image (HSI) applications (e.g., classification). This letter proposes an unsupervised BS approach based on a split-andmerge concept. This new approach provides relevant spectral sub-bands by splitting the adjacent bands without violating the physical meaning of the spectral data. Next, it merges highly correlated bands and sub-bands to reduce the dimensionality of the HSI. Experiments on three public data sets and comparison with state-of-the-art approaches show the efficiency of the proposed approach.