**Undergraduate Thesis**

The following paper develops the theories and methods used in a gesture recognition system implemented as a human-computer interface (HCI). The gesture recognition system recognizes four fundamental static hand gestures and variations for a total of nine gestures. The system uses a variation of the CAMSHIFT algorithm for hand tracking and a minimum distance classifier for classification. The Win32 API is utilized to perform the desired actions, which are determined by a microstate/macrostate architecture by which contextual information is used to correct any falsities in single frame classification. The state oriented model uses order statistics to provide corrections. The software, named MTrack, is implemented using Borland Delphi 7.0 and DirectX and is specifically designed for low-end desktop hardware. E.g. A 600MHz Pentium with commercial off the shelf (COTS) camera hardware.

Thesis | Software Demo | Presentation | Original Webpage

**Masters Thesis**

Hyperspectral unmixing is necessary for material abundance map (MAM) creation. Most unmixing algorithms search for a set of pure pixels, called endmembers, of which all other pixels in the image are linear combinations of this set. Hence, endmember extraction is an important process in the creation of useful material abundance maps. Material abundance maps are created using a three step process: estimation of the number of materials in an image, unmixing of the image to determine the spectral signatures (endmembers) of these fundamental materials, and finally, some type of constrained least squares algorithm using the recovered endmember spectra to generate the abundance maps. This thesis formally evaluates the first two steps of this process using simulated and real data. First, a common material count estimation algorithm, known as virtual dimensionality (VD), is examined. Second, three endmember extraction algorithms are evaluated: Automatic Target Generation Process (ATGP), ICA-Based Endmember Extraction Algorithm (ICA-EEA) and Vertex Component Analysis (VCA). Finally, the derivation of a constrained least squares technique is given from which the results of the first two steps are used as input to create abundance maps on real data from the AVIRIS sensor. This process serves as a means of qualitatively evaluating the efficacy of these algorithms on live data from which ground truth information could not be realized. The three unmixing algorithms arise from different schools of thought. The ICA-EEA uses independent component analysis (ICA) to isolate endmembers present in a scene. Conversely, ATGP and VCA work on the principle of orthogonality in that endmembers are extracted by iteratively projecting the data orthogonally to the current span of detected endmembers. The two methods differ in how they select the next orthogonal direction. Additionally, the authors of VCA state ICA based methods cannot perform well due to the sum-to-one constraint in linear endmember mixing. The results of this thesis prove otherwise. All methods require that pure pixels are present in the scene.

Thesis | Defense | Sample Latex Penn State Masters Thesis

**Course Projects**

CSE 485 – Dignal Image Processing I

- Effects of Spatial Resolution Changes on Quantization on Gray Level Images
- Image Transformation Using Boolean Operations / Component Analysis
- Contrast Enhancement, Histogram Equalization, Spatial Filtering, & Edge Detection
- Fourier Transform and Frequency Domain Filter Design
- Inverse Filtering
- Image Compression and Mathematical Morphology

CSE 585 – Dignal Image Processing II

- Mathematical Morphology: Binary Image Processing & Filtering
- Mathematical Morphology: Shape Analysis & Skeletonization
- Nonlinear Filtering and Anisotropic Diffusion
- Image Restoration Using Wiener Filtering

CSE 486 – Computer Vision I

- Image Transformations and Interpolation Methods
- Edge Detection and Image Filtering
- Hough Transform
- Disparity Maps and Depth Computations
- CAMSHIFT Tracking Algorithm

CSE 586 – Computer Vision II

- Continuous Adaptive Motion-based Person Understanding System (CAMPUS)
- Two Speedy Template Matching Algorithms Analyzed

EE 553 – Statistical Signal Processing

EE 556 – Neural Networks

METEO 597a – Remote Sensing of Earth Systems