Aboul Ella Hassanien (Abo)

This paper proposes a human thermal face recognition approach with two variants based on Random linear
Oracle (RLO) ensembles. For the two approaches, the Segmentation-based Fractal Texture Analysis (SFTA) algorithm was used for extracting features and the RLO ensemble classifier was used for recognizing the face from its thermal image. For the dimensionality reduction, one variant (SFTALDA-RLO) was used the technique of Linear Discriminant Analysis (LDA) while the other variant (SFTA-PCA-RLO) was used the Principal Component Analysis (PCA). The classifier’s model was built using the RLO classifier during the training phase and in the testing phase then this model was used to identify the unknown sample images. The two variants were evaluated using the Terravic Facial IR Database and the experimental results showed that the two variants achieved a good recognition rate at 94.12% which is better than related work.

Medical image enhancement is an essential process for superior disease diagnosis as well as for
detection of pathological lesion accurately. Computed Tomography (CT) is considered a vital medical
imaging modality to evaluate numerous diseases such as tumors and vascular lesions. However,
speckle noise corrupts the CT images and makes the clinical data analysis ambiguous.
Therefore, for accurate diagnosis, medical image enhancement is a must for noise removal and
sharp/clear images. In this work, a medical image enhancement algorithm has been proposed using
log transform in an optimization framework. In order to achieve optimization, a well-known
meta-heuristic algorithm, namely: Cuckoo search (CS) algorithm is used to determine the optimal
parameter settings for log transform. The performance of the proposed technique is studied on a
low contrast CT image dataset. Besides this, the results clearly show that the CS based approach
has superior convergence and fitness values compared to PSO as the CS converge faster that
proves the efficacy of the CS based technique. Finally, Image Quality Analysis (IQA) justifies the robustness >
of the proposed enhancement technique.

Geotagged photos carry hidden data about the surrounding area, and the owner of the photo. Moreover; Geotagged photos have background information about the user, where the alternative resources of Geo-spatial data lack background information. In this study, we propose identification for the circles of relations of the smartphone user from Geotagged photos. The proposed solution mainly depends on a framework, which is based on smartphone photo gallery. The framework extracts a degree of relation between smartphone user and circles of relations entities. Circles of relations incorporate closest people, places, where the participant visits, and interests. The circles of relations are represented in a social graph, which shows the clusters of social relations and interests of smartphone user. The social graph clarifies the nature and the degree of the relations for the participants. The results of framework introduced the relation between the level of variety of participant social relations, and the degree of relations.

Feature sets are always dependent, redundant and noisy in almost all application domains. These problems in The data always declined the performance of any given classifier as it make it difficult for the training phase to converge effectively and it affect also the running time for classification at operation and training time. In this work a system for feature selection based on multi-objective gray wolf optimization is proposed. The existing methods for feature selection either depend on the data description; filter-based methods, or depend on the classifier used; wrapper approaches. These two main approaches lakes of good performance and data description in the same system. In this work gray wolf optimization; a swarm-based optimization method, was employed to search the space of features to find optimal feature subset that both achieve data description with minor redundancy and keeps classification performance. At the early stages of optimization gray wolf uses filter-based principles to find a set of solutions with minor redundancy described by mutual information. At later stages of optimization wrapper approach is employed guided by classifier performance to further enhance the obtained solutions towards better classification performance. The proposed method is assessed against different common searching methods such as particle swarm optimization and genetic algorithm and also was assessed against different single objective systems. The proposed system achieves an advance over other searching methods and over the other single objective methods by testing over different UCI data sets and achieve much robustness and stability.

Diabetic retinopathy is a disease, which forms a severe threat on sight. It may reach to blindness among working age people. By analyzing and detecting of vasculature structures in retinal images, we can early detect the diabetes in advanced stages by comparison of its states of retinal blood vessels. In this paper, we present blood vessel segmentation approach, which can be used in computer based retinal image analysis to extract the retinal image vessels. Mathematical morphology and K-means clustering are used to segment the vessels. To enhance the blood vessels and suppress the background information, we perform smoothing operation on the retinal image using mathematical morphology. Then the enhanced image is segmented using K-means clustering algorithm. The proposed approach is tested on the DRIVE dataset and is compared with alternative approaches. Experimental results obtained by the proposed approach showed that it is effective as it achieved average accuracy of 95.10% and best accuracy of 96.25%.

This volume contains accepted papers presented at AECIA2014, the First International Afro-European Conference for Industrial Advancement. The aim of AECIA was to bring together the foremost experts as well as excellent young researchers from Africa, Europe, and the rest of the world to disseminate latest results from various fields of engineering, information, and communication technologies. The first edition of AECIA was organized jointly by Addis Ababa Institute of Technology, Addis Ababa University, and VSB - Technical University of Ostrava, Czech Republic and took place in Ethiopia's capital, Addis Ababa.

This article presents an automatic system for assessing water quality based on fish gills microscopic images. As fish gills are a good biomarker for assessing water quality, the proposed system uses fish gills microscopic images in order to detect water pollution. The proposed system consists of three phases; namely pre-processing, feature extraction, and classification phases. Since the shape is the main characteristic of fish gills microscopic images, the proposed system uses shape feature based on edge detection and wavelets transform for classifying the water-quality degree. Furthermore, it implemented Principal Components Analysis (PCA) along with Support Vector Machines (SVMs) algorithms for feature extraction and water quality degree classification. The datasets used for experiments were constructed based on real sample images for fish gills. Training dataset is divided into four classes representing the different histopathological changes and the corresponding water quality degrees. Experimental results showed that the proposed classification system has obtained water quality classification accuracy of 95.41%, using the SVMs linear kernel function and 10-fold cross validation with 37 images per class for training.