Learn More
This paper presents a new local facial feature descriptor, Local Gray Code Pattern (LGCP), for facial expression recognition in contrast to widely adopted Local Binary pattern. Local Gray Code Pattern (LGCP) characterizes both the texture and contrast information of facial components. The LGCP descriptor is obtained using local gray color intensity(More)
BACKGROUND Neonatal infections annually claim lives of 1.4 million neonates worldwide. Until now, there is no ideal diagnostic test for detecting sepsis and thus management of possible sepsis cases often depends on clinical algorithm leading to empirical treatment. This often results in unnecessary antibiotic use, which may lead to emergence of antibiotic(More)
BACKGROUND Group B Streptococcus (GBS) is a predominant cause of early-onset neonatal sepsis globally; however, the impact of this organism on the health of newborns in South Asia is debated, due in part to a paucity of community-based assessments. We estimated the prevalence and serotypes of GBS colonization of the umbilical cord stump and the association(More)
BACKGROUND Randomized trials from South Asia indicate umbilical cord chlorhexidine cleansing reduces mortality and omphalitis. No community-based data are available on bacteriological profile of the cord, early neonatal colonization dynamics, or impact of cord cleansing on colonizing organisms. Such data could clarify the design of scaled chlorhexidine(More)
This paper presents a new technique to extract the light invariant local feature for facial expression recognition. It is not only robust to monotonic gray-scale changes caused by light variations but also very simple to perform which makes it possible for analyzing images in challenging real-time settings. The local feature for a pixel is computed by(More)
BACKGROUND Insufficient knowledge of the etiology and risk factors for community-acquired neonatal infection in low-income countries is a barrier to designing appropriate intervention strategies for these settings to reduce the burden and treatment of young infant infection. To address these gaps, we are conducting the Aetiology of Neonatal Infection in(More)
Appearance based local feature methods are widely used for facial expression recognition because of their simplicity and high accuracy rates of recognition. However, the achieved accuracy rates and running time yet need to be improved. A new appearance based local feature method, called Local Distinctive Gradient Pattern (LDGP) is proposed in this paper. It(More)
Preface We express our gratitude to Allah Almighty for the courage He gave us to sustain the hard work. We cannot forget all the helpful teachers who helped us throughout our Endeavour for this lengthy period. We express our special thanks to Tony Larsson and Wagner de Morais for their support and feedback. We have thanks to offer to Ola Lundh for giving us(More)
BACKGROUND The Aetiology of Neonatal Infection in South Asia (ANISA) study aims to determine the etiology of neonatal infections in 5 population-based sites in Bangladesh, India and Pakistan. METHODS The main laboratory challenges in ANISA were selection and consistent implementation of laboratory methods at participating sites with varied infrastructure.(More)
BACKGROUND A centralized data management system was developed for data collection and processing for the Aetiology of Neonatal Infection in South Asia (ANISA) study. ANISA is a longitudinal cohort study involving neonatal infection surveillance and etiology detection in multiple sites in South Asia. The primary goal of designing such a system was to collect(More)