Project

# Title Team Members TA Documents Sponsor
1 Parallelizable Algorithm for Hyperspectral Biometrics
Akshay Malik
Christopher Baker
Timothee Bouhour
appendix0.pdf
design_document0.pdf
final_paper0.pdf
other0.pdf
other0.pdf
presentation0.pdf
proposal0.pdf
In the modern world unique person identification has become an increasing challenge, central to strategies in combating terrorism and crime to provide global security. Recent research has shown that hyperspectral imaging provides new and improved biometric data, which can be leveraged to meet this challenge by examining features in different spectral bands.

Our product uses hyperspectral imaging to correctly identify a given person from a database. This product will:

1) Use as an input existing raw data from hyperspectral sensors (from external sources) which would have, for each point in an image, both coordinates as well as intensity for a given range of hyperspectral bands.

2) Determine which points of the image to be used for analysis and comparison (such as: skin between the eyes, cheeks, forehead, and nose bridge).

3) Develop a comparison algorithm and use the parallel processing capabilities of a GPU to run this algorithm with the band data for these points and the data in the database in the most efficient way.

4) Output the closest match in the database and how similar it is to the target as a percentage.

5) Remotely activate a door locking mechanism if a match is found within a given accuracy.

We will preload our database with data gathered from a variety of test subjects, then try to match the original images as well as additional images of the same subjects to the database. Our stretch goal would be, if time permits, to enhance the algorithm to account for differences in facial expressions, makeup, lighting source, head orientation, etc.

Musical Hand

Ramsey Foote, Thomas MacDonald, Michelle Zhang

Musical Hand

Featured Project

# Musical Hand

Team Members:

- Ramesey Foote (rgfoote2)

- Michelle Zhang (mz32)

- Thomas MacDonald (tcm5)

# Problem

Musical instruments come in all shapes and sizes; however, transporting instruments often involves bulky and heavy cases. Not only can transporting instruments be a hassle, but the initial purchase and maintenance of an instrument can be very expensive. We would like to solve this problem by creating an instrument that is lightweight, compact, and low maintenance.

# Solution

Our project involves a wearable system on the chest and both hands. The left hand will be used to dictate the pitches of three “strings” using relative angles between the palm and fingers. For example, from a flat horizontal hand a small dip in one finger is associated with a low frequency. A greater dip corresponds to a higher frequency pitch. The right hand will modulate the generated sound by adding effects such as vibrato through lateral motion. Finally, the brains of the project will be the central unit, a wearable, chest-mounted subsystem responsible for the audio synthesis and output.

Our solution would provide an instrument that is lightweight and easy to transport. We will be utilizing accelerometers instead of flex sensors to limit wear and tear, which would solve the issue of expensive maintenance typical of more physical synthesis methods.

# Solution Components

The overall solution has three subsystems; a right hand, left hand, and a central unit.

## Subsystem 1 - Left Hand

The left hand subsystem will use four digital accelerometers total: three on the fingers and one on the back of the hand. These sensors will be used to determine the angle between the back of the hand and each of the three fingers (ring, middle, and index) being used for synthesis. Each angle will correspond to an analog signal for pitch with a low frequency corresponding to a completely straight finger and a high frequency corresponding to a completely bent finger. To filter out AC noise, bypass capacitors and possibly resistors will be used when sending the accelerometer signals to the central unit.

## Subsystem 2 - Right Hand

The right subsystem will use one accelerometer to determine the broad movement of the hand. This information will be used to determine how much of a vibrato there is in the output sound. This system will need the accelerometer, bypass capacitors (.1uF), and possibly some resistors if they are needed for the communication scheme used (SPI or I2C).

## Subsystem 3 - Central Unit

The central subsystem utilizes data from the gloves to determine and generate the correct audio. To do this, two microcontrollers from the STM32F3 series will be used. The left and right hand subunits will be connected to the central unit through cabling. One of the microcontrollers will receive information from the sensors on both gloves and use it to calculate the correct frequencies. The other microcontroller uses these frequencies to generate the actual audio. The use of two separate microcontrollers allows for the logic to take longer, accounting for slower human response time, while meeting needs for quicker audio updates. At the output, there will be a second order multiple feedback filter. This will get rid of any switching noise while also allowing us to set a gain. This will be done using an LM358 Op amp along with the necessary resistors and capacitors to generate the filter and gain. This output will then go to an audio jack that will go to a speaker. In addition, bypass capacitors, pull up resistors, pull down resistors, and the necessary programming circuits will be implemented on this board.

# Criterion For Success

The minimum viable product will consist of two wearable gloves and a central unit that will be connected together via cords. The user will be able to adjust three separate notes that will be played simultaneously using the left hand, and will be able to apply a sound effect using the right hand. The output audio should be able to be heard audibly from a speaker.

Project Videos