Search

This paper presents comparative evaluation of an application of deep convolutional neural networks (dCNNs) to age invariant face recognition. To this end, we use four distinct dCNN models, the AlexNet, VGGNet, GoogLeNet and ResNet. We assess their performance to recognize face images across aging variations, firstly by fine-tuning the models and secondly using them as face feature extractor. We also suggest a novel synthesized aging augmentation technique suitable for age-invariant face recognition using dCNNs. The face recognition experiments are conducted on three challenging FG-NET, MORPH and LAG aging datasets, and results are benchmarked with a simple CNN. The comparative study allows us to answer (i) when and why transfer learning or feature extraction strategies are useful in age-invariant face recognition scenarios, (ii) the potential of aging synthesized augmentation to increase accuracy and (iii) the choice of appropriate feature normalization and distance metrics to be used with deeply learned features. The extensive experiments, and valuable insights presented in this study can be extended to the design of effective age-invariant face recognition algorithms. [ABSTRACT FROM AUTHOR]

The requirement for effective image search, which motivates the use of Content-Based Image Retrieval (CBIR) and the search of similar multimedia contents on the basis of user query, remains an open research problem for computer vision applications. The application domains for Bag of Visual Words (BoVW) based image representations are object recognition, image classification and content-based image analysis. Interest point detectors are quantized in the feature space and the final histogram or image signature do not retain any detail about co-occurrences of features in the 2D image space. This spatial information is crucial, as it adversely affects the performance of an image classification-based model. The most notable contribution in this context is Spatial Pyramid Matching (SPM), which captures the absolute spatial distribution of visual words. However, SPM is sensitive to image transformations such as rotation, flipping and translation. When images are not well-aligned, SPM may lose its discriminative power. This paper introduces a novel approach to encoding the relative spatial information for histogram-based representation of the BoVW model. This is established by computing the global geometric relationship between pairs of identical visual words with respect to the centroid of an image. The proposed research is evaluated by using five different datasets. Comprehensive experiments demonstrate the robustness of the proposed image representation as compared to the state-of-the-art methods in terms of precision and recall values. [ABSTRACT FROM AUTHOR]

University buildings, such as student residence halls with year-round consistent energy demands, offer strong opportunities for Combined Heat and Power (CHP) systems. The economic and environmental feasibility of a CHP project is strongly linked with its optimum sizing. This study aims to undertake such an assessment for a CHP system for a student residence hall located in London, the United Kingdom (UK). The study also aims to undertake a sensitivity analysis to investigate the effect of different parameters on the project’s economics. Necessary data are collected via interviews with the University’s Energy Manager. Modeling of the CHP system is performed using the London South Bank University (LSBU, London, the UK) CHP model. Results demonstrate that optimum sizing of CHP is crucial for achieving higher economic and environmental benefits and strongly depends on the authenticity of the energy consumption data, based on which the CHP is being sized. Use of incorrect energy data could result in an undersized or oversized CHP system, where an oversized system will result in higher negative results compared to an undersized system. Finally, Monto Carlo statistical analysis shows that electricity price is the significant factor that could affect the project’s economics. With an increasing spark gap, the payback period decreases, and vice versa. [ABSTRACT FROM AUTHOR]

Universities in the United Kingdom that have installed Combined Heat and Power (CHP) technology are making good moves towards achieving their CO2 reduction targets. However, CHP may not always be an economical option for a university campus due to numerous factors. Identification of such factors is highly important before making an investment decision. A detailed technical, economic, and environmental feasibility of CHP is, therefore, indispensable. This study aims to undertake a detailed assessment of CHP for a typical university campus and attempts to highlight the significance of such factors. Necessary data and information were collected through site visits, whereas the CHP sizing was performed using the London South Bank University (LSBU) CHP model. The results suggest that there is a strong opportunity of installing a 230 kW CHP that will offset grid electricity and boilers thermal supply by 47% and 75%, respectively, and will generate financial and environmental yearly savings of £51k and 395 t/CO2, respectively. A wider spark gap decreases the payback period of the project and vice versa. The capital cost of the project could affect the project's economics due to factors, such as unavailability of space for CHP, complex existing infrastructure, and unavailability of a gas connection. [ABSTRACT FROM AUTHOR]