Hassan Al-Muhairi

Digital Arabic content: Challenges and opportunities

Todays Internet is enormously lacking Arabic language content. Although Internet users from the Arab world are increasing rapidly, the digital Arabic content still lacks serious research and development plans. In this paper, we present the main challenges facing the digital Arabic content industry and opportunities for developing the presence of Arabic language on the web at both individual and governmental levels. We also highlight recent initiatives within UAE which aim to increase the visibility of digital Arabic content. One example is the Arabic reCAPTCHA research project at Khalifa University.

RGRank: Ranking Semantically Related Genes

Biologists often need to know the set of genes that are semantically related to a given set of genes. However, most current similarity measures determine the semantic (biological meaning) similarities between the set rather than identifying the set. Moreover, these similarity measures determine the semantic similarities between the genes based solely on the proximity of their GO term annotations to each other in GO graph while overlooking the structural dependencies between these terms, which may lead to lower recall and precision of results. We propose in this paper a search engine called RGRank, which overcomes the limitations of current similarity measures outlined above as follows: (1) Given a set S of genes, RGRank would return a set of genes, where each gene in is semantically related to each gene in, (2) RGRank ranks gene results by relevance to their semantic similarities to the input genes, and (3) RGRank employs the concept of existence dependency to determine the structural dependencies among the GO terms annotating a given set of gene. We evaluated RGRank experimentally and compared it with three existing methods. Results showed marked improvement.

Landmark detection from 3D mesh facial models for image-based analysis of dysmorphology

Facial landmark detection is a task of interest for facial dysmorphology, an important factor in the diagnosis of genetic conditions. In this paper, we propose a framework for feature points detection from 3D face images. The method is based on 3D Constrained Local Model (CLM) which learns both global variations in the 3D facial scan and local changes around every vertex landmark. Compared to state of the art methods our framework is distinguished by the following novel aspects: 1) It operates on facial surfaces, 2) It allows fusion of shape and color information on the mesh surface, 3) It introduces the use of LBP descriptors on the mesh. We showcase our landmarks detection framework on a set of scans including down syndrome and control cases. We also validate our method through a series of quantitative experiments conducted with the publicly available Bosphorus database.

Cloud-based Arabic reCAPTCHA service: Design and architecture

reCAPTCHA is a popular technique used for web security. It distinguishes humans from computer programs to protect websites from automated abuse by presenting a challenge to be solved. reCAPTCHA utilizes human computation power used in solving these challenges to aid in increasing the accuracy of digitizing printed manuscripts. Although reCAPTCHA has been developed in many languages, to date, there is no available reCAPTCHA for the Arabic language. There is an immense need for the development of an Arabic reCAPTCHA service to increase the accuracy that existing OCRs currently lacks in digitizing Arabic manuscripts, and to aid in securing millions of Arabic websites. In this paper, we present a cloud-based design and architecture for an Arabic reCAPTCHA service, and we detail and describe key design and system components which include word classification algorithms, database schema design, and technology selection. We also study the inadequacy of existing popular OCRs in recognizing correctly Arabic printed text.

Computationally Efficient Quantitative Testing of Image Segmentation with a Genetic Algorithm

Quantitative testing of segmentation algorithms implies rigorous testing against ground truth segmentations. Though under-reported in the literature, the performance of a segmentation algorithm depends on the choice of input parameters. The paper reports wide variety both in evaluation time and segmentation results for an example mean-shift algorithm. When testing extends over an algorithmpsilas parameter space, then the search for satisfactory settings has a considerable cost in time. This paper considers the use of a genetic algorithm (GA) to avoid an exhaustive search. As application of the GA drastically reduces search times, the paper investigates how best to apply the GA in terms of initial candidate population, convergence speed, and application of a final polishing round. The GA parameter search forms part of a three-component computation environment aimed at automating the search and reducing the evaluation time. The first component relies on scripted testing and collation of results. The second component transfers to a commodity cluster computer. And the third component applies a genetic algorithm to avoid an exhaustive search.

A computationally efficient evaluation environment for image segmentation

An emphasis on quantitative testing of segmentation algorithms implies rigorous testing against ground truth segmentations. When testing extends over the algorithms parameter space, then the search for a best fit has a considerable cost in time. The paper reports wide variety both in evaluation time and segmentation results for an example mean-shift algorithm. This paper proposes a three-component computation environment aimed at automating the search and reducing the evaluation time. The first component relies on scripted testing and collation of results. The second component transfers to a commodity cluster computer. And the third component introduces a genetic algorithm to avoid an exhaustive search. Application of the genetic algorithm drastically reduces search times.

Landmarks detection on 3D face scans using local histogram descriptors

In this work, we exploit 3D Constrained Local Model (CLM) for facial landmark detection. Our approach integrates the geometric information of 3D face scans. The fast increase demand of 3D data invite to develop 3D image processing methods for many applications and especially for automatic landmark detection. The new step in this paper is the introduction of mesh histogram of gradients (meshHOG) as local descriptors around every landmark location. The proposed work is evaluated on the publicly available Bosphorus database. A comparison with the other descriptors mesh LBP and mesh SIFT are also depicted.

Facial landmarks detection using 3D constrained local model on mesh manifold

This paper proposes a novel 3D Constrained Local Models (CLM) approach applied for the detection of facial landmarks in 3D images. This approach capitalizes on the properties of Independent Component Analysis (ICA) to define appropriate priors of a face Point Distribution Model. Tailored to the mesh manifold modality, this approach address the limitations of the depth images which require pose normalization and suffer from the loss of the shape information caused by 2D projection. We validate this framework through a series of experiments conducted with the public Bosporus database, whereby it demonstrates a competitive performance compared to other state of the art methods.

Architectural design of a cloud-based reCAPTCHA service

reCAPTCHA is a security measure that guards web applications against automated abuse by presenting a random auto-generated challenge to users to solve. These challenges have to be devised to be hard to be solved by computers, yet easy for humans. In this paper, we present an architectural design for a cloud-based reCAPTCHA service and discuss key design issues. These issues include the extraction of individual word images from the scanned pages, optical character recognition (OCR) initial words classification, handling multiple users at the cloud-based service side, and usability and readability. We also show how our design addresses these issues at the implementation phase. It is worth noting that our reCAPTCHA service is designed for the Arabic language, but the underlying proposed architecture and design principles can be applied to any other language.

3D constrained local model with independent component analysis and non-Gaussian shape prior distribution: Application to 3D facial landmark detection

We present a novel statistical shape model and fitting process for the 3D Constrained Local Models (CLM), exploiting the properties of Independent Component Analysis (ICA), instead of the classic use of Principal Component Analysis (PCA), and adopting a non-Gaussian distribution of the shape prior information. Using ICA permits to exploit the real distribution of shape priors by adopting a Generalised Gaussian Distribution (GGD) model. Consequently, we derive a modified approach of the mean shift optimizer by using the Expectation-Maximization algorithms. We apply this novel method for the localization of face landmarks on 3D facial mesh models, which, to the best of our knowledge, is the first employment of the CLM variant on this kind of modality. Experiments conduced on the Bosphorus face database demonstrated that our approach outperforms state-of-the-art methods.