Digital & Image Signal Processing

If your innovative technology involves signal and image processing/pattern recognition, then I can help you fund, prototype, and publicize your value to funders, investors, and the general public.

I can do this because I have considerable experience in developing and maintaining windowed digital signal/image processing and pattern recognition applications using MATLAB, C, and Git under Linux, Mac OSX, and Windows.

This software development experience means that I can easily communicate with software engineers to develop effective proposals, marketing literature/videos, and training videos for software applications.

The following sections document my software experience & how I can help your software projects succeed.

Graphical User Interfaces for Phonetics Research

For the Phonetics Laboratory of Cornell University's Linguistics Department, I design MATLAB Graphical User Interfaces and MATLAB signal processing and pattern recognition applications that support the Lab's ongoing speech research.

My accomplishments thus far are:

Back To Top

DSP Software & Hardware for Medical Applications

  • Developed a classifier for diabetic laser doppler blood perfusion waveforms
  • Designed & analyzed fixed-point digital filters for microcontrollers using the MATLAB Signal Processing and Fixed-Point Filter Design Toolboxes.
  • Demonstrated a DSP-based laser doppler perfusion waveform processing system based on the TI 6713 DSK and TI's Code Composer Studio.

Back To Top

Image Processing for Military Applications

  • Researched and documented run-time characteristics of a model-based image pattern recognition methods for aircraft identification
  • Developed a windowed user interfaces under UNIX (SunView/X-Windows) for analyzing large images - used internally within the GE Military & Data Systems Operation.
  • Mapping image pattern recognition algorithms onto SIMD and MIMD parallel processing systems.
  • Masters Thesis researched the application of Artificial Intelligence techniques to one-dimensional signal spectral estimation.

Back To Top

Technical Details:

The page banner above is an eight-second spectrogram of a Northern Mockingbird.  The recording came from a  USGS bird song site.  I converted the .MP3 file to a .WAV file using Sound Forge and then used this MATLAB M-file to calculate the spectrogram and compare it with the time series

Back To Top