Digital Commons Network^™

Automatic Kinship Verification In Unconstrained Faces Using Deep Learning, Naman Kohli

Graduate Theses, Dissertations, and Problem Reports

Kinship verification has a number of applications such as organizing large collections of images and recognizing resemblances among humans. Identifying kinship relations has also garnered interest due to several potential applications in security and surveillance and organizing and tagging the enormous number of videos being uploaded on the Internet. This dissertation has a five-fold contribution where first, a study is conducted to gain insight into the kinship verification process used by humans. Besides this, two separate deep learning based methods are proposed to solve kinship verification in images and videos. Other contributions of this research include interlinking face verification with …

On Generative Adversarial Network Based Synthetic Iris Presentation Attack And Its Detection, Naman Kohli

Graduate Theses, Dissertations, and Problem Reports

Human iris is considered a reliable and accurate modality for biometric recognition due to its unique texture information. Reliability and accuracy of iris biometric modality have prompted its large-scale deployment for critical applications such as border control and national identification projects. The extensive growth of iris recognition systems has raised apprehensions about the susceptibility of these systems to various presentation attacks.

In this thesis, a novel iris presentation attack using deep learning based synthetically generated iris images is presented. Utilizing the generative capability of deep convolutional generative adversarial networks and iris quality metrics, a new framework, named as iDCGAN is …

A Deep Dive Into The Land Development Dynamics Of A Complex Landscape, Pariya Pourmohammadi

Graduate Theses, Dissertations, and Problem Reports

Land development is a complex and dynamic process simultaneously interacting with numerous environmental, cultural and economic procedures. In this research we studied past, present and future of land transformation in Appalachia. This dissertation is organized in three-essay format and each essay is focused on one aspect of land development processes in a sub-region in the Appalachian region. In the first essay, deep learning techniques are used to build predictive models for the land development. This study presets deconvolutional neural networks models in predicting land development. On the second essay, spatial data analysis and remote sensing are used to investigate the …

Quantifying Human Biological Age: A Machine Learning Approach, Syed Ashiqur Rahman

Graduate Theses, Dissertations, and Problem Reports

Quantifying human biological age is an important and difficult challenge. Different biomarkers and numerous approaches have been studied for biological age prediction, each with its advantages and limitations. In this work, we first introduce a new anthropometric measure (called Surface-based Body Shape Index, SBSI) that accounts for both body shape and body size, and evaluate its performance as a predictor of all-cause mortality. We analyzed data from the National Health and Human Nutrition Examination Survey (NHANES). Based on the analysis, we introduce a new body shape index constructed from four important anthropometric determinants of body shape and body size: body …