Displaying publications 1 - 20 of 162 in total

Abstract:
Sort:
  1. Abdulameer MH, Sheikh Abdullah SN, Othman ZA
    ScientificWorldJournal, 2014;2014:835607.
    PMID: 24790584 DOI: 10.1155/2014/835607
    Existing face recognition methods utilize particle swarm optimizer (PSO) and opposition based particle swarm optimizer (OPSO) to optimize the parameters of SVM. However, the utilization of random values in the velocity calculation decreases the performance of these techniques; that is, during the velocity computation, we normally use random values for the acceleration coefficients and this creates randomness in the solution. To address this problem, an adaptive acceleration particle swarm optimization (AAPSO) technique is proposed. To evaluate our proposed method, we employ both face and iris recognition based on AAPSO with SVM (AAPSO-SVM). In the face and iris recognition systems, performance is evaluated using two human face databases, YALE and CASIA, and the UBiris dataset. In this method, we initially perform feature extraction and then recognition on the extracted features. In the recognition process, the extracted features are used for SVM training and testing. During the training and testing, the SVM parameters are optimized with the AAPSO technique, and in AAPSO, the acceleration coefficients are computed using the particle fitness values. The parameters in SVM, which are optimized by AAPSO, perform efficiently for both face and iris recognition. A comparative analysis between our proposed AAPSO-SVM and the PSO-SVM technique is presented.
    Matched MeSH terms: Face*
  2. Abu A, Ngo CG, Abu-Hassan NIA, Othman SA
    BMC Bioinformatics, 2019 Feb 04;19(Suppl 13):548.
    PMID: 30717658 DOI: 10.1186/s12859-018-2548-9
    BACKGROUND: Indirect anthropometry (IA) is one of the craniofacial anthropometry methods to perform the measurements on the digital facial images. In order to get the linear measurements, a few definable points on the structures of individual facial images have to be plotted as landmark points. Currently, most anthropometric studies use landmark points that are manually plotted on a 3D facial image by the examiner. This method is time-consuming and leads to human biases, which will vary from intra-examiners to inter-examiners when involving large data sets. Biased judgment also leads to a wider gap in measurement error. Thus, this work aims to automate the process of landmarks detection to help in enhancing the accuracy of measurement. In this work, automated craniofacial landmarks (ACL) on a 3D facial image system was developed using geometry characteristics information to identify the nasion (n), pronasale (prn), subnasale (sn), alare (al), labiale superius (ls), stomion (sto), labiale inferius (li), and chelion (ch). These landmarks were detected on the 3D facial image in .obj file format. The IA was also performed by manually plotting the craniofacial landmarks using Mirror software. In both methods, once all landmarks were detected, the eight linear measurements were then extracted. Paired t-test was performed to check the validity of ACL (i) between the subjects and (ii) between the two methods, by comparing the linear measurements extracted from both ACL and AI. The tests were performed on 60 subjects (30 males and 30 females).

    RESULTS: The results on the validity of the ACL against IA between the subjects show accurate detection of n, sn, prn, sto, ls and li landmarks. The paired t-test showed that the seven linear measurements were statistically significant when p 

    Matched MeSH terms: Face/anatomy & histology*; User-Computer Interface
  3. Agbolade O, Nazri A, Yaakob R, Ghani AAA, Cheah YK
    PeerJ Comput Sci, 2020;6:e249.
    PMID: 33816901 DOI: 10.7717/peerj-cs.249
    Over the years, neuroscientists and psychophysicists have been asking whether data acquisition for facial analysis should be performed holistically or with local feature analysis. This has led to various advanced methods of face recognition being proposed, and especially techniques using facial landmarks. The current facial landmark methods in 3D involve a mathematically complex and time-consuming workflow involving semi-landmark sliding tasks. This paper proposes a homologous multi-point warping for 3D facial landmarking, which is verified experimentally on each of the target objects in a given dataset using 500 landmarks (16 anatomical fixed points and 484 sliding semi-landmarks). This is achieved by building a template mesh as a reference object and applying this template to each of the targets in three datasets using an artificial deformation approach. The semi-landmarks are subjected to sliding along tangents to the curves or surfaces until the bending energy between a template and a target form is minimal. The results indicate that our method can be used to investigate shape variation for multiple datasets when implemented on three databases (Stirling, FRGC and Bosphorus).
    Matched MeSH terms: Face
  4. Agbolade O, Nazri A, Yaakob R, Ghani AA, Cheah YK
    PLoS One, 2020;15(4):e0228402.
    PMID: 32271782 DOI: 10.1371/journal.pone.0228402
    BACKGROUND: The application of three-dimensional scan models offers a useful resource for studying craniofacial variation. The complex mathematical analysis for facial point acquisition in three-dimensional models has made many craniofacial assessments laborious.

    METHOD: This study investigates three-dimensional (3D) soft-tissue craniofacial variation, with relation to ethnicity, sex and age variables in British and Irish white Europeans. This utilizes a geometric morphometric approach on a subsampled dataset comprising 292 scans, taken from a Liverpool-York Head Model database. Shape variation and analysis of each variable are tested using 20 anchor anatomical landmarks and 480 sliding semi-landmarks.

    RESULTS: Significant ethnicity, sex, and age differences are observed for measurement covering major aspects of the craniofacial shape. The ethnicity shows subtle significant differences compared to sex and age; even though it presents the lowest classification accuracy. The magnitude of dimorphism in sex is revealed in the facial, nasal and crania measurement. Significant shape differences are also seen at each age group, with some distinct dimorphic features present in the age groups.

    CONCLUSIONS: The patterns of shape variation show that white British individuals have a more rounded head shape, whereas white Irish individuals have a narrower head shape. White British persons also demonstrate higher classification accuracy. Regarding sex patterns, males are relatively larger than females, especially in the mouth and nasal regions. Females presented with higher classification accuracy than males. The differences in the chin, mouth, nose, crania, and forehead emerge from different growth rates between the groups. Classification accuracy is best for children and senior adult age groups.

    Matched MeSH terms: Face/anatomy & histology*
  5. Agbolade O, Nazri A, Yaakob R, Ghani AA, Cheah YK
    Sci Rep, 2021 10 21;11(1):20767.
    PMID: 34675349 DOI: 10.1038/s41598-021-99944-z
    Angelman syndrome (AS) is one of the common genetic disorders that could emerge either from a 15q11-q13 deletion or paternal uniparental disomy (UPD) or imprinting or UBE3A mutations. AS comes with various behavioral and phenotypic variability, but the acquisition of subjects for experiment and automating the landmarking process to characterize facial morphology for Angelman syndrome variation investigation are common challenges. By automatically detecting and annotating subject faces, we collected 83 landmarks and 10 anthropometric linear distances were measured from 17 selected anatomical landmarks to account for shape variability. Statistical analyses were performed on the extracted data to investigate facial variation in each age group. There is a correspondence in the results achieved by relative warp (RW) of the principal component (PC) and the thin-plate spline (TPS) interpolation. The group is highly discriminated and the pattern of shape variability is higher in children than other groups when judged by the anthropometric measurement and principal component.
    Matched MeSH terms: Face/abnormalities*; Face/pathology
  6. Ahmed M. Mbarib, Mohammad Hamiruce Marhaban, Abdul Rahman Ramli
    MyJurnal
    Skin colour is an important visual cue for face detection, face recogmtlon, hand segmentation for gesture analysis and filtering of objectionable images. In this paper, the adaptive skin color detection model is proposed, based on two bivariate normal distribution models of the skin chromatic subspace, and on image segmentation using an automatic and adaptive multi-thresholding technique. Experimental results on images presenting a wide range of variations in lighting condition and background demonstrate the efficiency of the proposed skin-segmentation algorithm.
    Matched MeSH terms: Face
  7. Al-Khatib AR, Rajion ZA, Masudi SM, Hassan R, Townsend GC
    Homo, 2013 Aug;64(4):296-311.
    PMID: 23755965 DOI: 10.1016/j.jchb.2013.04.002
    The aim of this study was to evaluate the relationships of selected facial measurements with mesio-distal crown widths and dental arch dimensions in individuals with normal occlusions. A cross-sectional study was conducted on 276 subjects with Angle's Class I normal occlusions. Three-dimensional images of the face and dental casts were captured and analyzed using stereophotogrammetric systems. Significant correlations were found between the sagittal facial variables and both upper and lower dental arch dimensions and to lesser degree with the horizontal and vertical variables. The values of correlation coefficients calculated between facial and dental crown measurements ranged from .01 to .50 for upper teeth and .01 to .49 for lower teeth. The values of correlation coefficients between facial and upper dental arch dimensions ranged from .01 to .55 and those between facial and lower dental arch dimensions ranged from .01 to .60. A principal components analysis showed that the sagittal dimensions, face height, nose, labial fissure, binocular widths were positively associated with dental arch dimensions and mesio-distal crown diameters in males. On the other hand, only the sagittal variables were associated with dental dimensions in females. The results of this study confirm that positive associations exist between facial and dental arch dimensions. These relationships should be taken into consideration when attempts are made to modify dental arch size as part of orthodontic treatment. Moreover, these relationships are also relevant to prosthodontists involved with selecting tooth sizes that display optimal functional balance with the craniofacial structures.
    Matched MeSH terms: Face/anatomy & histology*
  8. Al-Khatib, Ali Rajih
    MyJurnal
    The surface facial imagings have many applications in medical fields. The recent past has seen great advances in three dimensional imaging which include laser scanning or stereophotogrammetry. Here, we reviewed various systems with reference to image acquisition, advantages and disadvantages. Examples of important clinical application with reference to the human face are also discussed. Finally, a 3D imaging system at Universiti Sains Malaysia (USM) is described.
    Matched MeSH terms: Face
  9. Alam MK, Mohd Noor NF, Basri R, Yew TF, Wen TH
    PLoS One, 2015;10(11):e0142914.
    PMID: 26562655 DOI: 10.1371/journal.pone.0142914
    This study aimed to investigate the association of facial proportion and its relation to the golden ratio with the evaluation of facial appearance among Malaysian population. This was a cross-sectional study with 286 randomly selected from Universiti Sains Malaysia (USM) Health Campus students (150 females and 136 males; 100 Malaysian Chinese, 100 Malaysian Malay and 86 Malaysian Indian), with the mean age of 21.54 ± 1.56 (Age range, 18-25). Facial indices obtained from direct facial measurements were used for the classification of facial shape into short, ideal and long. A validated structured questionnaire was used to assess subjects' evaluation of their own facial appearance. The mean facial indices of Malaysian Indian (MI), Malaysian Chinese (MC) and Malaysian Malay (MM) were 1.59 ± 0.19, 1.57 ± 0.25 and 1.54 ± 0.23 respectively. Only MC showed significant sexual dimorphism in facial index (P = 0.047; P<0.05) but no significant difference was found between races. Out of the 286 subjects, 49 (17.1%) were of ideal facial shape, 156 (54.5%) short and 81 (28.3%) long. The facial evaluation questionnaire showed that MC had the lowest satisfaction with mean score of 2.18 ± 0.97 for overall impression and 2.15 ± 1.04 for facial parts, compared to MM and MI, with mean score of 1.80 ± 0.97 and 1.64 ± 0.74 respectively for overall impression; 1.75 ± 0.95 and 1.70 ± 0.83 respectively for facial parts.
    Matched MeSH terms: Face
  10. Albajalan OB, Samsudin AR, Hassan R
    Eur J Orthod, 2011 Oct;33(5):509-14.
    PMID: 21118908 DOI: 10.1093/ejo/cjq108
    The aim of this study was to compare the skeletal and soft tissue patterns between obstructive sleep apnoea (OSA) patients and control group of non-OSA patients. Fifty Malays (32 males and 18 females) aged 18-65 years divided into two equal groups 25 (17 males and 8 females) with OSA and a control group 25 subjects (15 males and 10 females). Both groups were diagnosed using polysomnography. Nineteen variables related to craniofacial skeletal and soft tissue morphology were measured on lateral cephalometric films. Analysis of covariance was used to compare the means between the two groups. The results showed that OSA subjects had a significant increase in body mass index (BMI) and neck circumference than the control group. The soft palate and tongue were longer and thicker in OSA patients. In addition, upper, middle, and lower posterior airway spaces were narrower, the hyoid bone was more inferior and posterior, and the cranial base flexure angle was significantly acute when compared with the control group. The findings indicate that craniofacial abnormalities play significant roles in the pathogenesis of OSA in Malay patients.
    Matched MeSH terms: Face/anatomy & histology
  11. Alnned M. Mharib, Mohammad Hamiruce Marhaban, Abdul Rahman Ramli
    MyJurnal
    Skin detection has gained popularity and importance in the computer vision community. It is an essential step for important vision tasks such as the detection, tracking and recognition of face, segmentation of hand for gesture analysis, person identification, as well as video surveillance and filtering of objectionable web images. All these applications are based on the assumption that the regions of the human skin are already located. In the recent past, numerous techniques for skin colour modeling and recognition have been proposed. The aims of this paper are to compile the published pixel-based skin colour detection techniques to describe their key concepts and try to find out and summarize their advantages, disadvantages and characteristic features.
    Matched MeSH terms: Face
  12. Arnia F, Oktiana M, Saddami K, Munadi K, Roslidar R, Pradhan B
    Sensors (Basel), 2021 Jul 04;21(13).
    PMID: 34283116 DOI: 10.3390/s21134575
    Facial recognition has a significant application for security, especially in surveillance technologies. In surveillance systems, recognizing faces captured far away from the camera under various lighting conditions, such as in the daytime and nighttime, is a challenging task. A system capable of recognizing face images in both daytime and nighttime and at various distances is called Cross-Spectral Cross Distance (CSCD) face recognition. In this paper, we proposed a phase-based CSCD face recognition approach. We employed Homomorphic filtering as photometric normalization and Band Limited Phase Only Correlation (BLPOC) for image matching. Different from the state-of-the-art methods, we directly utilized the phase component from an image, without the need for a feature extraction process. The experiment was conducted using the Long-Distance Heterogeneous Face Database (LDHF-DB). The proposed method was evaluated in three scenarios: (i) cross-spectral face verification at 1m, (ii) cross-spectral face verification at 60m, and (iii) cross-spectral face verification where the probe images (near-infrared (NIR) face images) were captured at 1m and the gallery data (face images) was captured at 60 m. The proposed CSCD method resulted in the best recognition performance among the CSCD baseline approaches, with an Equal Error Rate (EER) of 5.34% and a Genuine Acceptance Rate (GAR) of 93%.
    Matched MeSH terms: Face
  13. Atiya N, Sulaiman H, Chong J, Ng KP
    J Infect Dev Ctries, 2015 Mar;9(3):313-6.
    PMID: 25771471 DOI: 10.3855/jidc.5208
    We report the first case of an immunocompromised adult patient presenting with cervicofacial lymphadenitis due to Mycobacterium haemophilum, confirmed using hsp65 gene sequencing and line-probe assays. In resource-limited settings, especially in developing countries, appropriate culture methods and rapid molecular diagnostic tools such as hsp65 gene sequencing for identification of this organism may not be readily available. This may cause M. haemophilum infections to go unrecognised or lead to delays in diagnosis. Lack of heightened awareness about the potential for this mycobacterial species to cause infections may also contribute to possible underestimation of M. haemophilum cases in the developing world.
    Matched MeSH terms: Face/pathology*
  14. Ayanniyi AA, Fasasi MK
    Malays J Med Sci, 2013 Jan;20(1):88-91.
    PMID: 23613660
    A hot water burn is a thermal injury that results in cell death. Thermal eye injury triggers inflammatory processes, including inflammatory cell influx and/or the activation of various inflammatory cells, which result in the rapid accumulation of extravascular fluid in the ocular tissue. The ocular effect depends on the temperature of the water, and the final visual outcome depends on the severity of the damage to the intraocular structures. We report a 23-year-old woman who experienced a facial hot water burn that resulted in blindness. The patient presented late to the hospital after the unsuccessful use of traditional medication. Facial burns are a known cause of blindness. Public health education on prompt hospital presentation, and resistance to the use of potentially harmful traditional medicine in facial burns is suggested.
    Matched MeSH terms: Face
  15. Balela, M.D.L., Lockman, Z., Azizan, A., Matsubara, E., Amorsolo , A.V. Jr.
    MyJurnal
    Monodispersed and size-tunable nanocrystalline cobalt (Co) particles in the range of 100 to 400 nm are prepared by the reduction of Co(II) species in propylene glycol. Control of the particle size is achieved by varying the initial Co(II) species concentration and by the addition of nucleating agents. Smaller Co particles are produced with increasing amounts of Co(II) species and in the presence of nucleating agents. X-ray diffraction analysis (XRD) shows that the Co particles are predominantly face-centered cubic crystals of about 8-14 nm. The Co particles are also ferromagnetic at room temperature.
    Matched MeSH terms: Face
  16. Banabilh SM, Samsudin AR, Suzina AH, Dinsuhaimi S
    Angle Orthod, 2010 Jan;80(1):37-42.
    PMID: 19852637 DOI: 10.2319/011509-26.1
    To test the null hypothesis that there is no difference in facial profile shape, malocclusion class, or palatal morphology in Malay adults with and without obstructive sleep apnea (OSA).
    Matched MeSH terms: Face*
  17. Banabilh SM, Suzina AH, Dinsuhaimi S, Samsudin AR, Singh GD
    Sleep Breath, 2009 Mar;13(1):19-24.
    PMID: 18763003 DOI: 10.1007/s11325-008-0211-9
    INTRODUCTION: Obstructive sleep apnea (OSA) and obesity are serious, widespread public health issues.

    OBJECTIVE: To localize and quantify geometric morphometric differences in facial soft tissue morphology in adults with and without OSA.

    MATERIALS AND METHODS: Eighty adult Malays, consisting of 40 patients with OSA and 40 non-OSA controls, were studied. Both groups were evaluated by the attending physician and through ambulatory sleep studies. 3-D stereophotogrammetry was used to capture facial soft tissues of both groups. The 3-D mean OSA and control facial configurations were computed and subjected to principal components analysis (PCA) and finite-element morphometry (FEM).

    RESULTS: The body mass index was significantly greater for the OSA group (32.3 kg/m(2) compared to 24.8 kg/m(2), p < 0.001). The neck circumference was greater for the OSA group (42.7 cm compared to 37.1 cm, p < 0.001). Using PCA, significant differences were found in facial shape between the two groups using the first two principal components, which accounted for 50% of the total shape change (p < 0.05). Using FEM, these differences were localized in the bucco-submandibular regions of the face predominantly, indicating an increase in volume of 7-22% (p < 0.05) for the OSA group.

    CONCLUSION: Craniofacial obesity in the bucco-submandibular regions is associated with OSA and may provide valuable screening information for the identification of patients with undiagnosed OSA.

    Matched MeSH terms: Face*
  18. Banabilh SM, Rajion ZA, Samsudin AR, Singh GD
    Int J Orthod Milwaukee, 2006;17(4):17-20.
    PMID: 17256439
    Facial soft tissues are a major determinant of treatment choice. When Class I and Class II malocclusions were compared using finite-element analysis, morphologic differences were localized and quantified. This study highlights the importance of determining the timing, magnitude and direction offacial growth prior to treatment to achieve stable results.
    Matched MeSH terms: Face*
  19. Barmou MM, Hussain SF, Abu Hassan MI
    Int Orthod, 2018 06;16(2):314-327.
    PMID: 29673688 DOI: 10.1016/j.ortho.2018.03.005
    AIM: The aim of the study was to assess the reliability and validity of cephalometric variables from MicroScribe-3DXL.

    MATERIALS AND METHODS: Seven cephalometric variables (facial angle, ANB, maxillary depth, U1/FH, FMA, IMPA, FMIA) were measured by a dentist in 60 Malay subjects (30 males and 30 females) with class I occlusion and balanced face. Two standard images were taken for each subject with conventional cephalometric radiography and MicroScribe-3DXL. All the images were traced and analysed. SPSS version 2.0 was used for statistical analysis with P-value was set at P<0.05.

    RESULTS: The results revealed a significant statistic difference in four measurements (U1/FH, FMA, IMPA, FMIA) with P-value range (0.00 to 0.03). The difference in the measurements was considered clinically acceptable. The overall reliability of MicroScribe-3DXL was 92.7% and its validity was 91.8%.

    CONCLUSION: The MicroScribe-3DXL is reliable and valid to most of the cephalometric variables with the advantages of saving time and cost. This is a promising device to assist in diverse areas in dental practice and research.

    Matched MeSH terms: Face
  20. Barua PD, Baygin N, Dogan S, Baygin M, Arunkumar N, Fujita H, et al.
    Sci Rep, 2022 Oct 14;12(1):17297.
    PMID: 36241674 DOI: 10.1038/s41598-022-21380-4
    Pain intensity classification using facial images is a challenging problem in computer vision research. This work proposed a patch and transfer learning-based model to classify various pain intensities using facial images. The input facial images were segmented into dynamic-sized horizontal patches or "shutter blinds". A lightweight deep network DarkNet19 pre-trained on ImageNet1K was used to generate deep features from the shutter blinds and the undivided resized segmented input facial image. The most discriminative features were selected from these deep features using iterative neighborhood component analysis, which were then fed to a standard shallow fine k-nearest neighbor classifier for classification using tenfold cross-validation. The proposed shutter blinds-based model was trained and tested on datasets derived from two public databases-University of Northern British Columbia-McMaster Shoulder Pain Expression Archive Database and Denver Intensity of Spontaneous Facial Action Database-which both comprised four pain intensity classes that had been labeled by human experts using validated facial action coding system methodology. Our shutter blinds-based classification model attained more than 95% overall accuracy rates on both datasets. The excellent performance suggests that the automated pain intensity classification model can be deployed to assist doctors in the non-verbal detection of pain using facial images in various situations (e.g., non-communicative patients or during surgery). This system can facilitate timely detection and management of pain.
    Matched MeSH terms: Face*; Databases, Factual
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links