• 3D data modelling and processing using partial differential equations.

      Ugail, Hassan (2007)
      In this paper we discuss techniques for 3D data modelling and processing where the data are usually provided as point clouds which arise from 3D scanning devices. The particular approaches we adopt in modelling 3D data involves the use of Partial Differential Equations (PDEs). In particular we show how the continuous and discrete versions of elliptic PDEs can be used for data modelling. We show that using PDEs it is intuitively possible to model data corresponding to complex scenes. Furthermore, we show that data can be stored in compact format in the form of PDE boundary conditions. In order to demonstrate the methodology we utlise several examples of practical nature.
    • 3D face recognition based on machine learning

      Qatawneh, S.; Ipson, Stanley S.; Qahwaji, Rami S.R.; Ugail, Hassan; 34000 (2008)
      3D facial data has a great potential for overcoming the problems of illumination and pose variation in face recognition. In this paper, we present a 3D facial system based on the machine learning. We used landmarks for feature extraction and Cascade Correlation neural network to make the final decision. Experiments are presented using 3D face images from the Face Recognition Grand Challenge database version 2.0. For CCNN using Jack-knife evaluation, an accuracy of 100% has been achieved for 7 faces with different expression, with 100% for both of specificity and sensitivity.
    • 3D facial data fitting using the biharmonic equation

      Ugail, Hassan (2006)
      This paper discusses how a boundary-based surface fitting approach can be utilised to smoothly reconstruct a given human face where the scan data corresponding to the face is provided. In particular, the paper discusses how a solution to the Biharmonic equation can be used to set up the corresponding boundary value problem. We show how a compact explicit solution method can be utilised for efficiently solving the chosen Biharmonic equation. Thus, given the raw scan data of a 3D face, we extract a series of profile curves from the data which can then be utilised as boundary conditions to solve the Biharmonic equation. The resulting solution provides us a continuous single surface patch describing the original face.
    • 3D modeling of magnetic field lines using SOHO/MDI magnetogram images

      Colak, Tufan; Qahwaji, Rami S.R.; Ipson, Stanley S.; Ugail, Hassan (2009-06-11)
      Solar images, along with other observational data, are very important for solar physicists and space weather researchers aiming to understand the way the Sun works and affects Earth. In this study a 3D modelling technique for visualizing solar magnetic field lines using solar images is presented. Photospheric magnetic field footpoints are detected from magnetogram images and using negative and positive magnetic footpoints, dipole pairs are associated according to their proximity. Then, 3D field line models are built using the calculated dipole coordinates, and mapped to detected pairs after coordinate transformations. Final 3D models are compared to extreme ultraviolet images and existing models and the results of visual comparisons are presented.
    • A database for facial behavioural analysis

      Yap, M.H.; Ugail, Hassan; Zwiggelaar, R. (2013)
      There is substantial interest in detection of human behaviour that may reveal people with deliberate malicious intent, who are engaging in deceit. Technology exists that is able to detect changes in facial patterns of movement and thermal signatures on the face. However, there is data deficiency in the research community for further study. Therefore this project aims to overcome the data deficiency in psychology study and algorithms development. A within-subjects design experiment was conducted, using immigration as a scenario for investigate participants in control and experimental conditions. A random sample of 32 volunteers were recruited, their age group is within 18 - 33. The study design required participants to answer questions on two topics, one as themselves and one as a predefined character. Data regarding visible and thermal images of facial movement and behaviour were collected. A rich FACS-coded database with high quality thermal images was established. Finally, recommendations for development and subsequent implementation of the facial analysis technique were made.
    • Auto-Parameterized Shape Grammar for Constructing Islamic Geometric Motif-Based Structures

      Sayed, Zahra; Ugail, Hassan; Palmer, Ian J.; Purdy, J.; Reeve, Carlton (2016-07-21)
      The complex formation of Islamic Geometric Patterns (IGP) is one of the distinctive features in Islamic art and architecture. Many have attempted to reproduce these patterns in digital form, using various pattern generation techniques, in 2D. Shape grammars are an e ective pattern generation method, providing good aesthetic results. In this pa- per we describe a novel approach in generating 3D IGP using the shape grammar method. The particular emphasis here is to generate the motifs (repeated units with the pattern) in 3D using parameterization. These can then be manipulated within the 3D space to construct architec- tural structures. In this work we have developed two distinctive Shape Grammars in 3D namely Parameterized Shape Grammar (PSG) and Auto-Parameterized Shape Grammar (APSG). Here the PSG generates the motifs and the APSG enables construction of the structures using the generated motifs. Both grammars are practically implemented as a 3D modelling tool within Autodesk Maya. The parameterization within each grammar is the key to generate both Islamic geometric motifs and Islamic geometric motif-based structures.
    • Automated Gland Detection in Colorectal Histopathological Images

      Al Zorgani, Maisun M.; Mehmood, Irfan; Ugail, Hassan (2022-01)
      Clinical morphological analysis of histopathological specimens is a successful manner for diagnosing benign and malignant diseases. Analysis of glandular architecture is a major challenge for colon histopathologists as a result of the difficulty of identifying morphological structures in glandular malignant tumours due to the distortion of glands boundaries, furthermore the variation in the appearance of staining specimens. For reliable analysis of colon specimens, several deep learning methods have exhibited encouraging performance in the glands automatic segmentation despite the challenges. In the histopathology field, the vast number of annotation images for training the deep learning algorithms is the major challenge. In this work, we propose a trainable Convolutional Neural Network (CNN) from end to end for detecting the glands automatically. More specifically, the Modified Res-U-Net is employed for segmenting the colorectal glands in Haematoxylin and Eosin (H&E) stained images for challenging Gland Segmentation (GlaS) dataset. The proposed Res-U-Net outperformed the prior methods that utilise U-Net architecture on the images of the GlaS dataset.
    • Automatic age and gender classification using supervised appearance model

      Bukar, Ali M.; Ugail, Hassan; Connah, David (2016-08-01)
      Age and gender classification are two important problems that recently gained popularity in the research community, due to their wide range of applications. Research has shown that both age and gender information are encoded in the face shape and texture, hence the active appearance model (AAM), a statistical model that captures shape and texture variations, has been one of the most widely used feature extraction techniques for the aforementioned problems. However, AAM suffers from some drawbacks, especially when used for classification. This is primarily because principal component analysis (PCA), which is at the core of the model, works in an unsupervised manner, i.e., PCA dimensionality reduction does not take into account how the predictor variables relate to the response (class labels). Rather, it explores only the underlying structure of the predictor variables, thus, it is no surprise if PCA discards valuable parts of the data that represent discriminatory features. Toward this end, we propose a supervised appearance model (sAM) that improves on AAM by replacing PCA with partial least-squares regression. This feature extraction technique is then used for the problems of age and gender classification. Our experiments show that sAM has better predictive power than the conventional AAM.
    • Automatic design and optimisation of thermoformed thin-walled structures.

      Ugail, Hassan; Wilson, M.J. (American Institute of Aeronautics and Astronautics., 2004)
      Here the design and functional optimisation of thermoformed thin-walled structures made from plastics is considered. Such objects are created in great numbers especially in the food packaging industry. In fact these objects are produced in such vast numbers each year, that one important task in the design of these objects is the minimisation of the amount of plastic used, subject to functional constraints. In this paper a procedure for achieving this is described, which involves the automatic optimisation of the mold shape taking into account the strength of the final object and its thickness distribution, thus reducing the need to perform inefficient and expensive `trial and error¿ experimentation using physical prototypes. An efficient technique for parameterising geometry is utilised here, enabling to create a wide variety of possible mold shapes on which appropriate analysis can be performed. The results of the analysis are used within an automatic optimisation routine enabling to find a design which satisfies user requirements. Thus, the paper describes a rational means for the automatic optimal design of composite thermoformed thin-walled structures.
    • Automatic Reconstruction and Web Visualization of Complex PDE Shapes

      Pang, M.; Sheng, Y.; Gonzalez Castro, Gabriela; Sourin, A.; Ugail, Hassan (2010)
    • Automatic shape optimisation of pharmaceutical tablets using Partial Differential Equations

      Ahmat, Norhayati; Gonzalez Castro, Gabriela; Ugail, Hassan (2014-01)
      Pharmaceutical tablets have been the most dominant form for drug delivery and most of them are used in the oral administration of drugs. These tablets need to be strong enough so that they can tolerate external stresses. Hence, during the design process, it is important to produce tablets with maximum mechanical strength while conserving the properties of powder form components. The mechanical properties of these tablets are assessed by measuring the tensile strength, which is commonly measured using diametrical or axial compression tests. This work describes the parametric design and optimisation of solid pharmaceutical tablets in cylindrical and spherical shapes, which are obtained using a formulation based on the use of Partial Differential Equations (PDEs) for shape design. The PDE-based formulation is capable of parameterised complex shapes using the information from some boundary curves that describe the shape. It is shown that the optimal design of pharmaceutical tablets with a particular volume and maximum strength can be obtained using an automatic design optimisation which is performed by combining the PDE method and a standard method for numerical optimisation.
    • The Biharmonic Eigenface

      Elmahmudi, Ali A.M.; Ugail, Hassan (2019-11)
      Principal component analysis (PCA) is an elegant mechanism that reduces the dimensionality of a dataset to bring out patterns of interest in it. The preprocessing of facial images for efficient face recognition is considered to be one of the epitomes among PCA applications. In this paper, we introduce a novel modification to the method of PCA whereby we propose to utilise the inherent averaging ability of the discrete Biharmonic operator as a preprocessing step. We refer to this mechanism as the BiPCA. Interestingly, by applying the Biharmonic operator to images, we can generate new images of reduced size while keeping the inherent features in them intact. The resulting images of lower dimensionality can significantly reduce the computational complexities while preserving the features of interest. Here, we have chosen the standard face recognition as an example to demonstrate the capacity of our proposed BiPCA method. Experiments were carried out on three publicly available datasets, namely the ORL, Face95 and Face96. The results we have obtained demonstrate that the BiPCA outperforms the traditional PCA. In fact, our experiments do suggest that, when it comes to face recognition, the BiPCA method has at least 25% improvement in the average percentage error rate.
    • The biometric characteristics of a smile

      Ugail, Hassan; Aldahoud, Ahmad (2019-04-18)
      Facial expressions have been studied looking for its diagnostic capabilities in mental health and clues for longevity, gender and other such personality traits. The use of facial expressions, especially the expression of smile, as a biometric has not been looked into great detail. However, research shows that a person can be identified from their behavioural traits including their emotional expressions. In this Chapter, we discuss a novel computational biometric model which can be derived from the smile expression. We discuss how the temporal components of a smile can be utilised to show that similarities in the smile exist for an individual and it can be enabled to create a tool which can be utilised as a biometric.
    • Blending using ODE swept surfaces with shape control and C1 continuity

      You, L.H.; Ugail, Hassan; Tang, B.P.; Jin, X.; You, X.Y.; Zhang, J.J. (2014-04-20)
      Surface blending with tangential continuity is most widely applied in computer-aided design, manufacturing systems, and geometric modeling. In this paper, we propose a new blending method to effectively control the shape of blending surfaces, which can also satisfy the blending constraints of tangent continuity exactly. This new blending method is based on the concept of swept surfaces controlled by a vector-valued fourth order ordinary differential equation (ODE). It creates blending surfaces by sweeping a generator along two trimlines and making the generator exactly satisfy the tangential constraints at the trimlines. The shape of blending surfaces is controlled by manipulating the generator with the solution to a vector-valued fourth order ODE. This new blending methods have the following advantages: (1) exact satisfaction of C1C1 continuous blending boundary constraints, (2) effective shape control of blending surfaces, (3) high computing efficiency due to explicit mathematical representation of blending surfaces, and (4) ability to blend multiple (more than two) primary surfaces.
    • Bradford Multi-Modal Gait Database: Gateway to Using Static Measurements to Create a Dynamic Gait Signature

      Alawar, Hamad M.M.A.; Ugail, Hassan; Kamala, Mumtaz A.; Connah, David (2016-01-06)
      Aims: To create a gait database with optimum accuracy of joint rotational data and an accu-rate representation of 3D volume, and explore the potential of using the database in studying the relationship between static and dynamic features of a human’s gait. Study Design: The study collected gait samples from 38 subjects, in which they were asked to walk, run, walk to run transition, and walk with a bag. The motion capture, video, and 3d measurement data extracted was used to analyse and build a correlation between features. Place and Duration of Study: The study was conducted in the University of Bradford. With the ethical approval from the University, 38 subjects’ motion and body volumes were recorded at the motion capture studio from May 2011- February 2013. Methodology: To date, the database includes 38 subjects (5 females, 33 males) conducting walk cycles with speed and load as covariants. A correlation analysis was conducted to ex-plore the potential of using the database to study the relationship between static and dynamic features. The volumes and surface area of body segments were used as static features. Phased-weighted magnitudes extracted through a Fourier transform of the rotation temporal data of the joints from the motion capture were used as dynamic features. The Pearson correlation coefficient is used to evaluate the relationship between the two sets of data. Results: A new database was created with 38 subjects conducting four forms of gait (walk, run, walk to run, and walking with a hand bag). Each subject recording included a total of 8 samples of each form of gait, and a 3D point cloud (representing the 3D volume of the subject). Using a Pvalue (P<.05) as a criterion for statistical significance, 386 pairs of features displayed a strong relationship. Conclusion: A novel database available to the scientific community has been created. The database can be used as an ideal benchmark to apply gait recognition techniques, and based on the correlation analysis, can offer a detailed perspective of the dynamics of gait and its relationship to volume. Further research in the relationship between static and dynamic features can contribute to the field of biomechanical analysis, use of biometrics in forensic applications, and 3D virtual walk simulation.
    • Burns Depth Assessment Using Deep Learning Features

      Abubakar, Aliyu; Ugail, Hassan; Smith, K.M.; Bukar, Ali M.; Elmahmudi, Ali (2020-12)
      Burns depth evaluation is a lifesaving task and very challenging that requires objective techniques to accomplish. While the visual assessment is the most commonly used by surgeons, its accuracy reliability ranges between 60 and 80% and subjective that lacks any standard guideline. Currently, the only standard adjunct to clinical evaluation of burn depth is Laser Doppler Imaging (LDI) which measures microcirculation within the dermal tissue, providing the burns potential healing time which correspond to the depth of the injury achieving up to 100% accuracy. However, the use of LDI is limited due to many factors including high affordability and diagnostic costs, its accuracy is affected by movement which makes it difficult to assess paediatric patients, high level of human expertise is required to operate the device, and 100% accuracy possible after 72 h. These shortfalls necessitate the need for objective and affordable technique. Method: In this study, we leverage the use of deep transfer learning technique using two pretrained models ResNet50 and VGG16 for the extraction of image patterns (ResFeat50 and VggFeat16) from a a burn dataset of 2080 RGB images which composed of healthy skin, first degree, second degree and third-degree burns evenly distributed. We then use One-versus-One Support Vector Machines (SVM) for multi-class prediction and was trained using 10-folds cross validation to achieve optimum trade-off between bias and variance. Results: The proposed approach yields maximum prediction accuracy of 95.43% using ResFeat50 and 85.67% using VggFeat16. The average recall, precision and F1-score are 95.50%, 95.50%, 95.50% and 85.75%, 86.25%, 85.75% for both ResFeat50 and VggFeat16 respectively. Conclusion: The proposed pipeline achieved a state-of-the-art prediction accuracy and interestingly indicates that decision can be made in less than a minute whether the injury requires surgical intervention such as skin grafting or not.
    • Characterization of micro-scale surface features using Partial Differential Equations

      Gonzalez Castro, Gabriela; Spares, Robert; Ugail, Hassan; Whiteside, Benjamin R.; Sweeney, John (2010)
    • A comparative study between Biharmonic Bezier surfaces and Biharmonic extremal surfaces

      Monterde, J.; Ugail, Hassan (ACTA Press, 2009-06-11)
      Given a prescribed boundary of a Bezier surface we compare the Bezier surfaces generated by two different methods, i.e. the Bezier surface minimising the Biharmonic functional and the unique Bezier surface solution of the Biharmonic equation with prescribed boundary. Although often the two types of surfaces look visually the same, we show that they are indeed different. In this paper we provide a theoretical argument showing why the two types of surfaces are not always the same.
    • Computation of curvatures over discrete geometry using biharmonic surfaces

      Ugail, Hassan (2008)
      The computation of curvature quantities over discrete geometry is often required when processing geometry composed of meshes. Curvature information is often important for the purpose of shape analysis, feature recognition and geometry segmentation. In this paper we present a method for accurate estimation of curvature on discrete geometry especially those composed of meshes. We utilise a method based on fitting a continuous surface arising from the solution of the Biharmonic equation subject to suitable boundary conditions over a 1-ring neighbourhood of the mesh geometry model. This enables us to accurately determine the curvature distribution of the local area. We show how the curvature can be computed efficiently by means of utilising an analytic solution representation of the chosen Biharmonic equation. In order to demonstrate the method we present a series of examples whereby we show how the curvature can be efficiently computed over complex geometry which are represented discretely by means of mesh models.
    • Computational analysis of smile weight distribution across the face for accurate distinction between genuine and posed smiles

      Al-dahoud, Ahmad; Ugail, Hassan (2018)
      In this paper, we report the results of our recent research into the understanding of the exact distribution of a smile across the face, especially the distinction in the weight distribution of a smile between a genuine and a posed smile. To do this, we have developed a computational framework for the analysis of the dynamic motion of various parts of the face during a facial expression, in particular, for the smile expression. The heart of our dynamic smile analysis framework is the use of optical flow intensity variation across the face during a smile. This can be utilised to efficiently map the dynamic motion of individual regions of the face such as the mouth, cheeks and areas around the eyes. Thus, through our computational framework, we infer the exact distribution of weights of the smile across the face. Further, through the utilisation of two publicly available datasets, namely the CK+ dataset with 83 subjects expressing posed smiles and the MUG dataset with 35 subjects expressing genuine smiles, we show there is a far greater activity or weight distribution around the regions of the eyes in the case of a genuine smile.