Physical Sciences and Mathematics Commons^™

Semantic Adversarial Attack On Support Vector Machine, Yessica Rodriguez

Theses and Dissertations

Despite the breakthroughs in machine learning, most classifiers are not robust against adversarial attacks. They can be easily fooled by adversarial examples. These examples can be created in a variety of ways. In this thesis, the ideas of detecting edges or critical pixels in an image are investigated that could be used for fooling classifiers. Identifying those critical pixels in an image can lead the way to fix the vulnerabilities and thus making it robust against cyber-attacks. For testing, a Support Vector Machine (SVM) is used to see the success of the adversarial examples generated.

Framework For Kernel Based Bm3d Algorithm, Mena Abdelrahman Massoud

Electronic Thesis and Dissertation Repository

Patch-based approaches such as Block Matching and 3D collaborative Filtering (BM3D) algorithm represent the current state-of-the-art in image denoising. However, BM3D still suffers from degradation in performance in smooth areas as well as loss of image details, specifically in the presence of high noise levels.

Integrating shape adaptive methods with BM3D improves the denoising outcome including the visual quality of the denoised image; and also maintains image details. In this study, we proposed a framework that produces multiple images using various shapes. These images were aggregated at the pixel or patch levels for both stages in BM3D, and when appropriately …

Road Sign Recognition System On Raspberry Pi, Enis Bilgin, Stefan Robila

Department of Computer Science Faculty Scholarship and Creative Works

Digital image processing, i.e. the use of computer systems to process pictures, has applications in many fields, including of medicine, space exploration, geology and oceanography and continues to increase in its applicability. The main objective of this paper is to demonstrate the ability of image processing algorithms on a small computing platform. Specifically we created a road sign recognition system based on an embedded system that reads and recognizes speed signs. The paper describes the characteristics of speed signs, requirements and difficulties behind implementing a real-time base system with embedded system, and how to deal with numbers using image processing …

Cyfrowe Przetwarzanie Zdjęć Satelitarnych, Przemysław Kupidura, Piotr Podlasiak

Przemysław Kupidura

No abstract provided.

Management Of Land Use Land Cover Through The Application Of Remote Sensing, Geographic Information Systems And Simulation, Praveen Jha

Graduate Doctoral Dissertations

Deforestation and degradation of forest areas, including those in the Protected Areas (PAs), are major concerns in India. There were 2 broad objectives of the study: the technological objective pertained to the development of state-of-art programs that could serve as Decision Support Systems while finalizing plans and policy interventions, while the other objective aimed at generating geo-spatial data in 2 PAs. A part of the Eastern Himalaya biodiversity hotspot, Manas Tiger Reserve (MTR), Assam, India having an area of 2837.12 sq km and an important part of Rajaji-Corbett Tiger Conservation Unit, Rajaji National Park (RNP), Uttarakhand, India, having an area …

Management Of Land Use Land Cover Through The Application Of Remote Sensing, Geographic Information Systems And Simulation, Praveen Jha

Praveen Jha Dr

Deforestation and degradation of forest areas, including those in the Protected Areas (PAs), are major concerns in India. There were 2 broad objectives of the study: the technological objective pertained to the development of state-of-art programs that could serve as Decision Support Systems while finalizing plans and policy interventions, while the other objective aimed at generating geo-spatial data in 2 PAs. A part of the Eastern Himalaya biodiversity hotspot, Manas Tiger Reserve (MTR), Assam, India having an area of 2837.12 sq km and an important part of Rajaji-Corbett Tiger Conservation Unit, Rajaji National Park (RNP), Uttarakhand, India, having an area …

Cleaning Of Rivers Through The Application Of Advanced Technologies, Praveen Jha Dr

Praveen Jha Dr

Despite immense drain on our scarce resources, rivers remain polluted. Waste disposal into rivers on top of meager to absent infrastructural facilities, including treatment facilities, are the most important drivers of pollution. Unscientific development paradigm devoid of adequate environmental safeguards and failure of forestry sector to cope up with the challenge has led to the deteriorated condition of green cover and water. Several state-of-art geo-spatial programs developed by the author would be applied for generating optimum state-of-art plan. Three state-of-art geo-spatial programs - Multi-Algorithm Automation Program (MAAP), Data Automatic Modification Program (DAMP) and Multi-Stage Simulation Program (MUSSIP) - developed primarily …

Impervious Surfaces Mapping Using High Resolution Satellite Imagery, Tahmina Shirmeen

Electronic Theses and Dissertations

In recent years, impervious surfaces have emerged not only as an indicator of the degree of urbanization, but also as an indicator of environmental quality. As impervious surface area increases, storm water runoff increases in velocity, quantity, temperature and pollution load. Any of these attributes can contribute to the degradation of natural hydrology and water quality. Various image processing techniques have been used to identify the impervious surfaces, however, most of the existing impervious surface mapping tools used moderate resolution imagery. In this project, the potential of standard image processing techniques to generate impervious surface data for change detection analysis …

Drinking Water Optimum Supply System (Dwoss) Through The Application Of Advanced Technologies, Praveen Jha Dr

Praveen Jha Dr

Paradigm shift in the approach for planning regarding supply of drinking water is mandatory since the current DPRs are unscientific and expensive. Planning for an optimum Drinking Water Supply System (ODWSS) that includes - optimization of Water Source Point (WSP), Water Treatment System (WTS), Water Storage Systems (WSSs), Water Distribution Points (WDP) and Water Supply Network (WSN); scientific estimation of long term demand of drinking water; minimization of physical and financial resources required for the plan implementation; water conservation and sanitation – could be done by applying several state-of-art geo-spatial programs developed by the author. Three programs - Multi-Algorithm Automation …

Optimization Of Check Dams Through The Application Of Advanced Technologies, Praveen Jha Dr

Praveen Jha Dr

Scientific planning for conserving water and while minimizing the financial resources requirement for its implementation could be done through application of advanced technological programs developed by the author. Three state-of-art geo-spatial programs - Multi-Algorithm Automation Program (MAAP), Water Analysis Program (WAP) and Check Dam Optimization Program (CDOP) - would be used. MAAP produces land use land cover (lulc) map primarily by undertaking Digital Image Processing (DIP) of satellite data in an automated fashion using Artificial Intelligence (AI). WAP, a hydrology modeling program, would be used to generate information related to watershed, water flow, water accumulation etc. CDOP, coupled with MAAP …

Management Of Forests Through The Application Of Advanced Technologies, Praveen Jha Dr

Praveen Jha Dr

Several state-of-art geo-spatial programs developed by the author could be applied to generate technological pathways for providing an integrated solution to the loads of problems in the forests in the most scientific, objective and effective manner so that the management prescriptions incorporating policy interventions may prove to be highly successful. Three state-of-art geo-spatial programs - Multi-Algorithm Automation Program (MAAP), Data Automatic Modification Program (DAMP) and Multi-Stage Simulation Program (MUSSIP) – developed to address the pertinent issues of conservation and sustainability could be used extensively. Based on satellite data, MAAP produces land use land cover (lulc) map of the present period, …

Radar Imagery Filtering With Use Of The Mathematical Morphology Operations, Przemysław Kupidura, Piotr Koza

Przemysław Kupidura

This paper concerns the application of mathematical morphology operations for suppression of speckle from radar satellite images. Different traditional widely-used filters are compared with the morphological alternate filters, especially with the filter with multiple structuring function. The comprehensive comparison of the traditional filters is presented, as well as the background on mathematical morphology and morphological filters. Then the evaluation of compared filters applied on TerraSAR-X images is presented.